RT2 Publications: Cyberdisturbance modelling and detection for Edge Computing
2025
Huraysi, Talea; Sun, Rui; Duan, Haoran; Adu-Duodu, Kwabena; Ranjan, Rajiv; Wei, Bo; Shah, Tejal
Seeing the unseen: Intrusion attack detection in connected autonomous vehicles Journal Article
In: High-Confidence Computing, 2025, ISSN: 2667-2952.
@article{Huraysi2025,
title = {Seeing the unseen: Intrusion attack detection in connected autonomous vehicles},
author = {Talea Huraysi and Rui Sun and Haoran Duan and Kwabena Adu-Duodu and Rajiv Ranjan and Bo Wei and Tejal Shah},
doi = {10.1016/j.hcc.2025.100375},
issn = {2667-2952},
year = {2025},
date = {2025-11-00},
urldate = {2025-11-00},
journal = {High-Confidence Computing},
publisher = {Elsevier BV},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Duan, Haoran; Shao, Shuai; Zhai, Bing; Shah, Tejal; Han, Jungong; Ranjan, Rajiv
Parameter Efficient Fine-Tuning for Multi-modal Generative Vision Models with Möbius-Inspired Transformation Journal Article
In: Int J Comput Vis, vol. 133, no. 7, pp. 4590–4603, 2025, ISSN: 1573-1405.
@article{Duan2025,
title = {Parameter Efficient Fine-Tuning for Multi-modal Generative Vision Models with Möbius-Inspired Transformation},
author = {Haoran Duan and Shuai Shao and Bing Zhai and Tejal Shah and Jungong Han and Rajiv Ranjan},
doi = {10.1007/s11263-025-02398-3},
issn = {1573-1405},
year = {2025},
date = {2025-07-00},
urldate = {2025-07-00},
journal = {Int J Comput Vis},
volume = {133},
number = {7},
pages = {4590–4603},
publisher = {Springer Science and Business Media LLC},
abstract = {<jats:title>Abstract</jats:title>
<jats:p>The rapid development of multimodal generative vision models has drawn scientific curiosity. Notable advancements, such as OpenAI’s ChatGPT and Stable Diffusion, demonstrate the potential of combining multimodal data for generative content. Nonetheless, customising these models to specific domains or tasks is challenging due to computational costs and data requirements. Conventional fine-tuning methods take redundant processing resources, motivating the development of parameter-efficient fine-tuning technologies such as adapter module, low-rank factorization and orthogonal fine-tuning. These solutions selectively change a subset of model parameters, reducing learning needs while maintaining high-quality results. Orthogonal fine-tuning, regarded as a reliable technique, preserves semantic linkages in weight space but has limitations in its expressive powers. To better overcome these constraints, we provide a simple but innovative and effective transformation method inspired by Möbius geometry, which replaces conventional orthogonal transformations in parameter-efficient fine-tuning. This strategy improved fine-tuning’s adaptability and expressiveness, allowing it to capture more data patterns. Our strategy, which is supported by theoretical understanding and empirical validation, outperforms existing approaches, demonstrating competitive improvements in generation quality for key generative tasks.
</jats:p>},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
<jats:title>Abstract</jats:title>
<jats:p>The rapid development of multimodal generative vision models has drawn scientific curiosity. Notable advancements, such as OpenAI’s ChatGPT and Stable Diffusion, demonstrate the potential of combining multimodal data for generative content. Nonetheless, customising these models to specific domains or tasks is challenging due to computational costs and data requirements. Conventional fine-tuning methods take redundant processing resources, motivating the development of parameter-efficient fine-tuning technologies such as adapter module, low-rank factorization and orthogonal fine-tuning. These solutions selectively change a subset of model parameters, reducing learning needs while maintaining high-quality results. Orthogonal fine-tuning, regarded as a reliable technique, preserves semantic linkages in weight space but has limitations in its expressive powers. To better overcome these constraints, we provide a simple but innovative and effective transformation method inspired by Möbius geometry, which replaces conventional orthogonal transformations in parameter-efficient fine-tuning. This strategy improved fine-tuning’s adaptability and expressiveness, allowing it to capture more data patterns. Our strategy, which is supported by theoretical understanding and empirical validation, outperforms existing approaches, demonstrating competitive improvements in generation quality for key generative tasks.
</jats:p>
<jats:p>The rapid development of multimodal generative vision models has drawn scientific curiosity. Notable advancements, such as OpenAI’s ChatGPT and Stable Diffusion, demonstrate the potential of combining multimodal data for generative content. Nonetheless, customising these models to specific domains or tasks is challenging due to computational costs and data requirements. Conventional fine-tuning methods take redundant processing resources, motivating the development of parameter-efficient fine-tuning technologies such as adapter module, low-rank factorization and orthogonal fine-tuning. These solutions selectively change a subset of model parameters, reducing learning needs while maintaining high-quality results. Orthogonal fine-tuning, regarded as a reliable technique, preserves semantic linkages in weight space but has limitations in its expressive powers. To better overcome these constraints, we provide a simple but innovative and effective transformation method inspired by Möbius geometry, which replaces conventional orthogonal transformations in parameter-efficient fine-tuning. This strategy improved fine-tuning’s adaptability and expressiveness, allowing it to capture more data patterns. Our strategy, which is supported by theoretical understanding and empirical validation, outperforms existing approaches, demonstrating competitive improvements in generation quality for key generative tasks.
</jats:p>
Miao, Xingyu; Duan, Haoran; Bai, Yang; Shah, Tejal; Song, Jun; Long, Yang; Ranjan, Rajiv; Shao, Ling
Laser: Efficient Language-Guided Segmentation in Neural Radiance Fields Journal Article
In: IEEE Trans. Pattern Anal. Mach. Intell., vol. 47, no. 5, pp. 3922–3934, 2025, ISSN: 2160-9292.
@article{Miao2025,
title = {Laser: Efficient Language-Guided Segmentation in Neural Radiance Fields},
author = {Xingyu Miao and Haoran Duan and Yang Bai and Tejal Shah and Jun Song and Yang Long and Rajiv Ranjan and Ling Shao},
doi = {10.1109/tpami.2025.3535916},
issn = {2160-9292},
year = {2025},
date = {2025-05-00},
urldate = {2025-05-00},
journal = {IEEE Trans. Pattern Anal. Mach. Intell.},
volume = {47},
number = {5},
pages = {3922–3934},
publisher = {Institute of Electrical and Electronics Engineers (IEEE)},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Zhang, Yumin; Duan, Haoran; Sun, Rui; Cheng, Yue; Shah, Tejal; Ranjan, Rajiv; Wei, Bo
LAGD: Local Topological-Alignment and Global Semantic-Deconstruction for Incremental 3D Semantic Segmentation Journal Article
In: AAAI, vol. 39, no. 21, pp. 22677–22685, 2025, ISSN: 2374-3468.
@article{Zhang2025,
title = {LAGD: Local Topological-Alignment and Global Semantic-Deconstruction for Incremental 3D Semantic Segmentation},
author = {Yumin Zhang and Haoran Duan and Rui Sun and Yue Cheng and Tejal Shah and Rajiv Ranjan and Bo Wei},
doi = {10.1609/aaai.v39i21.34427},
issn = {2374-3468},
year = {2025},
date = {2025-04-11},
urldate = {2025-04-11},
journal = {AAAI},
volume = {39},
number = {21},
pages = {22677–22685},
publisher = {Association for the Advancement of Artificial Intelligence (AAAI)},
abstract = {<jats:p>Numerous deep learning-based works focusing on 3D semantic segmentation have been proposed and have achieved impressive performance. However, due to the catastrophic forgetting, existing methods will degrade dramatically in a real-world scenario where new 3D semantic categories are arriving continually. Straightforwardly applying typical class-incremental learning methods on 3D data even aggravates forgetting due to the irregular and noisy geometric structure. Aiming to address this realistic challenge, from the perspective of capturing local topological characteristics and mitigating global semantic shift, we propose a unified framework named Local topological Alignment and Global semantic Deconstruction (LAGD) to incrementally learn semantic knowledge of novel 3D categories while maintaining performance on previously learned knowledge. Specifically, we develop a novel Interaction Topological-aware Alignment (ITA) to maintain the learned knowledge efficiently by capturing the local geometric characteristics with interacted adjacent state-specific knowledge. Besides, to mitigate the forgetting caused by the global semantic shift, we deconstruct the logits into positive and negative parts which are distilled separately, achieving an elaborate distillation process in terms of Semantic-knowledge Deconstruction Distillation (SDD). With the cooperation of ITA and SDD, LAGD achieves a sota performance, especially in the long-term incremental learning scenario. Extensive experimental results illustrate the superiority of our proposed LAGD.</jats:p>},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
<jats:p>Numerous deep learning-based works focusing on 3D semantic segmentation have been proposed and have achieved impressive performance. However, due to the catastrophic forgetting, existing methods will degrade dramatically in a real-world scenario where new 3D semantic categories are arriving continually. Straightforwardly applying typical class-incremental learning methods on 3D data even aggravates forgetting due to the irregular and noisy geometric structure. Aiming to address this realistic challenge, from the perspective of capturing local topological characteristics and mitigating global semantic shift, we propose a unified framework named Local topological Alignment and Global semantic Deconstruction (LAGD) to incrementally learn semantic knowledge of novel 3D categories while maintaining performance on previously learned knowledge. Specifically, we develop a novel Interaction Topological-aware Alignment (ITA) to maintain the learned knowledge efficiently by capturing the local geometric characteristics with interacted adjacent state-specific knowledge. Besides, to mitigate the forgetting caused by the global semantic shift, we deconstruct the logits into positive and negative parts which are distilled separately, achieving an elaborate distillation process in terms of Semantic-knowledge Deconstruction Distillation (SDD). With the cooperation of ITA and SDD, LAGD achieves a sota performance, especially in the long-term incremental learning scenario. Extensive experimental results illustrate the superiority of our proposed LAGD.</jats:p>
Adu-Duodu, Kwabena; Wilson, Stanly; Li, Yinhao; Oladimeji, Aanuoluwapo; Huraysi, Talea; Barati, Masoud; Perera, Charith; Solaiman, Ellis; Rana, Omer; Ranjan, Rajiv; Shah, Tejal
A Circular Construction Product Ontology for End-of-Life Decision-Making Bachelor Thesis
2025.
@bachelorthesis{Adu-Duodu2025,
title = {A Circular Construction Product Ontology for End-of-Life Decision-Making},
author = {Kwabena Adu-Duodu and Stanly Wilson and Yinhao Li and Aanuoluwapo Oladimeji and Talea Huraysi and Masoud Barati and Charith Perera and Ellis Solaiman and Omer Rana and Rajiv Ranjan and Tejal Shah},
doi = {10.1145/3672608.3707870},
year = {2025},
date = {2025-03-31},
urldate = {2025-03-31},
pages = {1943–1952},
publisher = {ACM},
keywords = {},
pubstate = {published},
tppubtype = {bachelorthesis}
}
Sun, Rui; Zhang, Yumin; Ojha, Varun; Shah, Tejal; Duan, Haoran; Wei, Bo; Ranjan, Rajiv
Exemplar-condensed Federated Class-incremental Learning Miscellaneous
2025.
@misc{sun2025exemplarcondensedfederatedclassincrementallearning,
title = {Exemplar-condensed Federated Class-incremental Learning},
author = {Rui Sun and Yumin Zhang and Varun Ojha and Tejal Shah and Haoran Duan and Bo Wei and Rajiv Ranjan},
url = {https://arxiv.org/abs/2412.18926},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Shi, Xiufang; Zhang, Wei; Wu, Mincheng; Liu, Guangyi; Wen, Zhenyu; He, Shibo; Shah, Tejal; Ranjan, Rajiv
Dataset Distillation-based Hybrid Federated Learning on Non-IID Data Miscellaneous
2025.
@misc{shi2025datasetdistillationbasedhybridfederated,
title = {Dataset Distillation-based Hybrid Federated Learning on Non-IID Data},
author = {Xiufang Shi and Wei Zhang and Mincheng Wu and Guangyi Liu and Zhenyu Wen and Shibo He and Tejal Shah and Rajiv Ranjan},
url = {https://arxiv.org/abs/2409.17517},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Zhang, Yumin; Gao, Yan; Duan, Haoran; Guo, Hanqing; Shah, Tejal; Ranjan, Rajiv; Wei, Bo
FedSCA: Federated Tuning with Similarity-guided Collaborative Aggregation for Heterogeneous Medical Image Segmentation Miscellaneous
2025.
@misc{zhang2025fedscafederatedtuningsimilarityguided,
title = {FedSCA: Federated Tuning with Similarity-guided Collaborative Aggregation for Heterogeneous Medical Image Segmentation},
author = {Yumin Zhang and Yan Gao and Haoran Duan and Hanqing Guo and Tejal Shah and Rajiv Ranjan and Bo Wei},
url = {https://arxiv.org/abs/2503.15390},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
2024
Yang, Huanqi; Li, Zhenjiang; Luo, Chengwen; Wei, Bo; Xu, Weitao
InaudibleKey2.0: Deep Learning-Empowered Mobile Device Pairing Protocol Based on Inaudible Acoustic Signals Journal Article
In: IEEE/ACM Trans. Networking, vol. 32, no. 5, pp. 4160–4174, 2024, ISSN: 1558-2566.
@article{Yang2024,
title = {InaudibleKey2.0: Deep Learning-Empowered Mobile Device Pairing Protocol Based on Inaudible Acoustic Signals},
author = {Huanqi Yang and Zhenjiang Li and Chengwen Luo and Bo Wei and Weitao Xu},
doi = {10.1109/tnet.2024.3407783},
issn = {1558-2566},
year = {2024},
date = {2024-10-00},
urldate = {2024-10-00},
journal = {IEEE/ACM Trans. Networking},
volume = {32},
number = {5},
pages = {4160–4174},
publisher = {Institute of Electrical and Electronics Engineers (IEEE)},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Li, Zheng; Saldías-Vallejos, Nicolás; Seco, Diego; Rodríguez, María Andrea; Ranjan, Rajiv
Long Live the Image: On Enabling Resilient Production Database Containers for Microservice Applications Journal Article
In: IIEEE Trans. Software Eng., vol. 50, no. 9, pp. 2363–2378, 2024, ISSN: 1939-3520.
@article{Li2024b,
title = {Long Live the Image: On Enabling Resilient Production Database Containers for Microservice Applications},
author = {Zheng Li and Nicolás Saldías-Vallejos and Diego Seco and María Andrea Rodríguez and Rajiv Ranjan},
doi = {10.1109/tse.2024.3436623},
issn = {1939-3520},
year = {2024},
date = {2024-09-00},
urldate = {2024-09-00},
journal = {IIEEE Trans. Software Eng.},
volume = {50},
number = {9},
pages = {2363–2378},
publisher = {Institute of Electrical and Electronics Engineers (IEEE)},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Kayan, Hakan; Heartfield, Ryan; Rana, Omer; Burnap, Pete; Perera, Charith
CASPER: Context-Aware IoT Anomaly Detection System for Industrial Robotic Arms Journal Article
In: ACM Trans. Internet Things, vol. 5, no. 3, pp. 1–36, 2024, ISSN: 2577-6207.
@article{Kayan2024,
title = {CASPER: Context-Aware IoT Anomaly Detection System for Industrial Robotic Arms},
author = {Hakan Kayan and Ryan Heartfield and Omer Rana and Pete Burnap and Charith Perera},
doi = {10.1145/3670414},
issn = {2577-6207},
year = {2024},
date = {2024-08-31},
urldate = {2024-08-31},
journal = {ACM Trans. Internet Things},
volume = {5},
number = {3},
pages = {1–36},
publisher = {Association for Computing Machinery (ACM)},
abstract = {<jats:p>Industrial cyber-physical systems (ICPS) are widely employed in supervising and controlling critical infrastructures, with manufacturing systems that incorporate industrial robotic arms being a prominent example. The increasing adoption of ubiquitous computing technologies in these systems has led to benefits such as real-time monitoring, reduced maintenance costs, and high interconnectivity. This adoption has also brought cybersecurity vulnerabilities exploited by adversaries disrupting manufacturing processes via manipulating actuator behaviors. Previous incidents in the industrial cyber domain prove that adversaries launch sophisticated attacks rendering network-based anomaly detection mechanisms insufficient as the “physics” involved in the process is overlooked. To address this issue, we propose an IoT-based cyber-physical anomaly detection system that can detect motion-based behavioral changes in an industrial robotic arm. We apply both statistical and state-of-the-art machine learning methods to real-time Inertial Measurement Unit data collected from an edge development board attached to an arm doing a pick-and-place operation. To generate anomalies, we modify the joint velocity of the arm. Our goal is to create an air-gapped secondary protection layer to detect “physical” anomalies without depending on the integrity of network data, thus augmenting overall anomaly detection capability. Our empirical results show that the proposed system, which utilizes 1D convolutional neural networks, can successfully detect motion-based anomalies on a real-world industrial robotic arm. The significance of our work lies in its contribution to developing a comprehensive solution for ICPS security, which goes beyond conventional network-based methods.</jats:p>},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
<jats:p>Industrial cyber-physical systems (ICPS) are widely employed in supervising and controlling critical infrastructures, with manufacturing systems that incorporate industrial robotic arms being a prominent example. The increasing adoption of ubiquitous computing technologies in these systems has led to benefits such as real-time monitoring, reduced maintenance costs, and high interconnectivity. This adoption has also brought cybersecurity vulnerabilities exploited by adversaries disrupting manufacturing processes via manipulating actuator behaviors. Previous incidents in the industrial cyber domain prove that adversaries launch sophisticated attacks rendering network-based anomaly detection mechanisms insufficient as the “physics” involved in the process is overlooked. To address this issue, we propose an IoT-based cyber-physical anomaly detection system that can detect motion-based behavioral changes in an industrial robotic arm. We apply both statistical and state-of-the-art machine learning methods to real-time Inertial Measurement Unit data collected from an edge development board attached to an arm doing a pick-and-place operation. To generate anomalies, we modify the joint velocity of the arm. Our goal is to create an air-gapped secondary protection layer to detect “physical” anomalies without depending on the integrity of network data, thus augmenting overall anomaly detection capability. Our empirical results show that the proposed system, which utilizes 1D convolutional neural networks, can successfully detect motion-based anomalies on a real-world industrial robotic arm. The significance of our work lies in its contribution to developing a comprehensive solution for ICPS security, which goes beyond conventional network-based methods.</jats:p>
Wei, Bo; Xu, Weitao; Gao, Mingcen; Lan, Guohao; Li, Kai; Luo, Chengwen; Zhang, Jin
SolarKey: Battery-free Key Generation Using Solar Cells Journal Article
In: ACM Trans. Sen. Netw., vol. 20, no. 1, pp. 1–24, 2024, ISSN: 1550-4867.
@article{Wei2023,
title = {SolarKey: Battery-free Key Generation Using Solar Cells},
author = {Bo Wei and Weitao Xu and Mingcen Gao and Guohao Lan and Kai Li and Chengwen Luo and Jin Zhang},
doi = {10.1145/3605780},
issn = {1550-4867},
year = {2024},
date = {2024-01-31},
urldate = {2024-01-31},
journal = {ACM Trans. Sen. Netw.},
volume = {20},
number = {1},
pages = {1–24},
publisher = {Association for Computing Machinery (ACM)},
abstract = {<jats:p>Solar cells have been widely used for offering energy for Internet of Things (IoT) devices. Recently, solar cells have also been used as sensors for context awareness sensing due to their sensitivity to varying lighting conditions. In this article, we are the first to use solar cells for symmetric key generation. To generate symmetric keys, we take advantage of photovoltage measurements generated from solar cells equipped with a pair of IoT devices. Symmetric keys are essential for pairing IoT devices and further securing wireless communication. Despite the sensitivity to varying lighting conditions, challenges still remain for the use of solar cells for key generation, such as time unsynchronisation and noisy measurements. To solve these challenges, we design a novel key generation framework, SolarKey, which includes the starting point detection and a compressed sensing-based two-tier key reconciliation method. Extensive experiments have been conducted to evaluate the performance of our proposed key generation method in various environments, which shows the proposed method can improve the key matching rate by up to 25%. We also conduct security analysis and the randomness test, which shows that SolarKey is resilient to common attacks such as the eavesdropping attack and the imitating attack and sufficiently random.</jats:p>},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
<jats:p>Solar cells have been widely used for offering energy for Internet of Things (IoT) devices. Recently, solar cells have also been used as sensors for context awareness sensing due to their sensitivity to varying lighting conditions. In this article, we are the first to use solar cells for symmetric key generation. To generate symmetric keys, we take advantage of photovoltage measurements generated from solar cells equipped with a pair of IoT devices. Symmetric keys are essential for pairing IoT devices and further securing wireless communication. Despite the sensitivity to varying lighting conditions, challenges still remain for the use of solar cells for key generation, such as time unsynchronisation and noisy measurements. To solve these challenges, we design a novel key generation framework, SolarKey, which includes the starting point detection and a compressed sensing-based two-tier key reconciliation method. Extensive experiments have been conducted to evaluate the performance of our proposed key generation method in various environments, which shows the proposed method can improve the key matching rate by up to 25%. We also conduct security analysis and the randomness test, which shows that SolarKey is resilient to common attacks such as the eavesdropping attack and the imitating attack and sufficiently random.</jats:p>
Al-Ameen, Shamil; Sudharsan, Bharath; Al-Taie, Roua; Shah, Tejal; Ranjan, Rajiv
LEAP: Lifelong Learning Edge-Cloud Adaptive Fused Framework for Mobility Prediction Proceedings Article
In: 2024 IEEE International Conference on Big Data (BigData), pp. 6707-6716, 2024.
@inproceedings{10825926,
title = {LEAP: Lifelong Learning Edge-Cloud Adaptive Fused Framework for Mobility Prediction},
author = {Shamil Al-Ameen and Bharath Sudharsan and Roua Al-Taie and Tejal Shah and Rajiv Ranjan},
doi = {10.1109/BigData62323.2024.10825926},
year = {2024},
date = {2024-01-01},
urldate = {2024-01-01},
booktitle = {2024 IEEE International Conference on Big Data (BigData)},
pages = {6707-6716},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Miao, Xingyu; Duan, Haoran; Ojha, Varun; Song, Jun; Shah, Tejal; Long, Yang; Ranjan, Rajiv
Dreamer XL: Towards High-Resolution Text-to-3D Generation via Trajectory Score Matching Miscellaneous
2024.
@misc{miao2024dreamerxlhighresolutiontextto3d,
title = {Dreamer XL: Towards High-Resolution Text-to-3D Generation via Trajectory Score Matching},
author = {Xingyu Miao and Haoran Duan and Varun Ojha and Jun Song and Tejal Shah and Yang Long and Rajiv Ranjan},
url = {https://arxiv.org/abs/2405.11252},
year = {2024},
date = {2024-01-01},
urldate = {2024-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Duan, Haoran; Sun, Rui; Ojha, Varun; Shah, Tejal; Huang, Zhuoxu; Ouyang, Zizhou; Huang, Yawen; Long, Yang; Ranjan, Rajiv
Dual Variational Knowledge Attention for Class Incremental Vision Transformer Proceedings Article
In: 2024 International Joint Conference on Neural Networks (IJCNN), pp. 1-8, 2024.
@inproceedings{10650317,
title = {Dual Variational Knowledge Attention for Class Incremental Vision Transformer},
author = {Haoran Duan and Rui Sun and Varun Ojha and Tejal Shah and Zhuoxu Huang and Zizhou Ouyang and Yawen Huang and Yang Long and Rajiv Ranjan},
doi = {10.1109/IJCNN60899.2024.10650317},
year = {2024},
date = {2024-01-01},
urldate = {2024-01-01},
booktitle = {2024 International Joint Conference on Neural Networks (IJCNN)},
pages = {1-8},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Sun, Rui; Zhang, Yumin; Shah, Tejal; Sun, Jiahao; Zhang, Shuoying; Li, Wenqi; Duan, Haoran; Wei, Bo; Ranjan, Rajiv
From Sora What We Can See: A Survey of Text-to-Video Generation Miscellaneous
2024.
@misc{sun2024soraseesurveytexttovideo,
title = {From Sora What We Can See: A Survey of Text-to-Video Generation},
author = {Rui Sun and Yumin Zhang and Tejal Shah and Jiahao Sun and Shuoying Zhang and Wenqi Li and Haoran Duan and Bo Wei and Rajiv Ranjan},
url = {https://arxiv.org/abs/2405.10674},
year = {2024},
date = {2024-01-01},
urldate = {2024-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Al-Ameen, Shamil; Sudharsan, Bharath; Vijayakumar, Tejus; Szydlo, Tomasz; Shah, Tejal; Ranjan, Rajiv
Poly Instance Recurrent Neural Network for Real-time Lifelong Learning at the Low-power Edge Proceedings Article
In: 2024 IEEE International Conference on Big Data (BigData), pp. 5907-5916, 2024.
@inproceedings{10825026,
title = {Poly Instance Recurrent Neural Network for Real-time Lifelong Learning at the Low-power Edge},
author = {Shamil Al-Ameen and Bharath Sudharsan and Tejus Vijayakumar and Tomasz Szydlo and Tejal Shah and Rajiv Ranjan},
doi = {10.1109/BigData62323.2024.10825026},
year = {2024},
date = {2024-01-01},
urldate = {2024-01-01},
booktitle = {2024 IEEE International Conference on Big Data (BigData)},
pages = {5907-5916},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Zhang, Yumin; Miao, Xingyu; Duan, Haoran; Wei, Bo; Shah, Tejal; Long, Yang; Ranjan, Rajiv
ExactDreamer: High-Fidelity Text-to-3D Content Creation via Exact Score Matching Miscellaneous
2024.
@misc{zhang2024exactdreamerhighfidelitytextto3dcontent,
title = {ExactDreamer: High-Fidelity Text-to-3D Content Creation via Exact Score Matching},
author = {Yumin Zhang and Xingyu Miao and Haoran Duan and Bo Wei and Tejal Shah and Yang Long and Rajiv Ranjan},
url = {https://arxiv.org/abs/2405.15914},
year = {2024},
date = {2024-01-01},
urldate = {2024-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Alqattan, Duaa S.; Sun, Rui; Liang, Huizhi; Nicosia, Guiseppe; Snasel, Vaclav; Ranjan, Rajiv; Ojha, Varun
Security Assessment of Hierarchical Federated Deep Learning Book Chapter
In: Lecture Notes in Computer Science, pp. 202–217, Springer Nature Switzerland, 2024, ISBN: 9783031723476.
@inbook{Alqattan2024d,
title = {Security Assessment of Hierarchical Federated Deep Learning},
author = {Duaa S. Alqattan and Rui Sun and Huizhi Liang and Guiseppe Nicosia and Vaclav Snasel and Rajiv Ranjan and Varun Ojha},
doi = {10.1007/978-3-031-72347-6_14},
isbn = {9783031723476},
year = {2024},
date = {2024-00-00},
urldate = {2024-00-00},
booktitle = {Lecture Notes in Computer Science},
pages = {202–217},
publisher = {Springer Nature Switzerland},
keywords = {},
pubstate = {published},
tppubtype = {inbook}
}
2023
Dwivedi, Rudresh; Dave, Devam; Naik, Het; Singhal, Smiti; Omer, Rana; Patel, Pankesh; Qian, Bin; Wen, Zhenyu; Shah, Tejal; Morgan, Graham; Ranjan, Rajiv
Explainable AI (XAI): Core Ideas, Techniques, and Solutions Journal Article
In: ACM Comput. Surv., vol. 55, no. 9, pp. 1–33, 2023, ISSN: 1557-7341.
@article{Dwivedi2023,
title = {Explainable AI (XAI): Core Ideas, Techniques, and Solutions},
author = {Rudresh Dwivedi and Devam Dave and Het Naik and Smiti Singhal and Rana Omer and Pankesh Patel and Bin Qian and Zhenyu Wen and Tejal Shah and Graham Morgan and Rajiv Ranjan},
doi = {10.1145/3561048},
issn = {1557-7341},
year = {2023},
date = {2023-09-30},
urldate = {2023-09-30},
journal = {ACM Comput. Surv.},
volume = {55},
number = {9},
pages = {1–33},
publisher = {Association for Computing Machinery (ACM)},
abstract = {<jats:p>As our dependence on intelligent machines continues to grow, so does the demand for more transparent and interpretable models. In addition, the ability to explain the model generally is now the gold standard for building trust and deployment of artificial intelligence systems in critical domains. Explainable artificial intelligence (XAI) aims to provide a suite of machine learning techniques that enable human users to understand, appropriately trust, and produce more explainable models. Selecting an appropriate approach for building an XAI-enabled application requires a clear understanding of the core ideas within XAI and the associated programming frameworks. We survey state-of-the-art programming techniques for XAI and present the different phases of XAI in a typical machine learning development process. We classify the various XAI approaches and, using this taxonomy, discuss the key differences among the existing XAI techniques. Furthermore, concrete examples are used to describe these techniques that are mapped to programming frameworks and software toolkits. It is the intention that this survey will help stakeholders in selecting the appropriate approaches, programming frameworks, and software toolkits by comparing them through the lens of the presented taxonomy.</jats:p>},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
<jats:p>As our dependence on intelligent machines continues to grow, so does the demand for more transparent and interpretable models. In addition, the ability to explain the model generally is now the gold standard for building trust and deployment of artificial intelligence systems in critical domains. Explainable artificial intelligence (XAI) aims to provide a suite of machine learning techniques that enable human users to understand, appropriately trust, and produce more explainable models. Selecting an appropriate approach for building an XAI-enabled application requires a clear understanding of the core ideas within XAI and the associated programming frameworks. We survey state-of-the-art programming techniques for XAI and present the different phases of XAI in a typical machine learning development process. We classify the various XAI approaches and, using this taxonomy, discuss the key differences among the existing XAI techniques. Furthermore, concrete examples are used to describe these techniques that are mapped to programming frameworks and software toolkits. It is the intention that this survey will help stakeholders in selecting the appropriate approaches, programming frameworks, and software toolkits by comparing them through the lens of the presented taxonomy.</jats:p>
Dwivedi, Rudresh; Dave, Devam; Naik, Het; Singhal, Smiti; Omer, Rana; Patel, Pankesh; Qian, Bin; Wen, Zhenyu; Shah, Tejal; Morgan, Graham; Ranjan, Rajiv
Explainable AI (XAI): Core Ideas, Techniques, and Solutions Journal Article
In: ACM Comput. Surv., vol. 55, no. 9, pp. 1–33, 2023, ISSN: 1557-7341.
@article{Dwivedi2023b,
title = {Explainable AI (XAI): Core Ideas, Techniques, and Solutions},
author = {Rudresh Dwivedi and Devam Dave and Het Naik and Smiti Singhal and Rana Omer and Pankesh Patel and Bin Qian and Zhenyu Wen and Tejal Shah and Graham Morgan and Rajiv Ranjan},
doi = {10.1145/3561048},
issn = {1557-7341},
year = {2023},
date = {2023-09-30},
urldate = {2023-09-30},
journal = {ACM Comput. Surv.},
volume = {55},
number = {9},
pages = {1–33},
publisher = {Association for Computing Machinery (ACM)},
abstract = {<jats:p>As our dependence on intelligent machines continues to grow, so does the demand for more transparent and interpretable models. In addition, the ability to explain the model generally is now the gold standard for building trust and deployment of artificial intelligence systems in critical domains. Explainable artificial intelligence (XAI) aims to provide a suite of machine learning techniques that enable human users to understand, appropriately trust, and produce more explainable models. Selecting an appropriate approach for building an XAI-enabled application requires a clear understanding of the core ideas within XAI and the associated programming frameworks. We survey state-of-the-art programming techniques for XAI and present the different phases of XAI in a typical machine learning development process. We classify the various XAI approaches and, using this taxonomy, discuss the key differences among the existing XAI techniques. Furthermore, concrete examples are used to describe these techniques that are mapped to programming frameworks and software toolkits. It is the intention that this survey will help stakeholders in selecting the appropriate approaches, programming frameworks, and software toolkits by comparing them through the lens of the presented taxonomy.</jats:p>},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
<jats:p>As our dependence on intelligent machines continues to grow, so does the demand for more transparent and interpretable models. In addition, the ability to explain the model generally is now the gold standard for building trust and deployment of artificial intelligence systems in critical domains. Explainable artificial intelligence (XAI) aims to provide a suite of machine learning techniques that enable human users to understand, appropriately trust, and produce more explainable models. Selecting an appropriate approach for building an XAI-enabled application requires a clear understanding of the core ideas within XAI and the associated programming frameworks. We survey state-of-the-art programming techniques for XAI and present the different phases of XAI in a typical machine learning development process. We classify the various XAI approaches and, using this taxonomy, discuss the key differences among the existing XAI techniques. Furthermore, concrete examples are used to describe these techniques that are mapped to programming frameworks and software toolkits. It is the intention that this survey will help stakeholders in selecting the appropriate approaches, programming frameworks, and software toolkits by comparing them through the lens of the presented taxonomy.</jats:p>
Dwivedi, Rudresh; Dave, Devam; Naik, Het; Singhal, Smiti; Omer, Rana; Patel, Pankesh; Qian, Bin; Wen, Zhenyu; Shah, Tejal; Morgan, Graham; Ranjan, Rajiv
Explainable AI (XAI): Core Ideas, Techniques, and Solutions Journal Article
In: ACM Comput. Surv., vol. 55, no. 9, pp. 1–33, 2023, ISSN: 1557-7341.
@article{Dwivedi2023c,
title = {Explainable AI (XAI): Core Ideas, Techniques, and Solutions},
author = {Rudresh Dwivedi and Devam Dave and Het Naik and Smiti Singhal and Rana Omer and Pankesh Patel and Bin Qian and Zhenyu Wen and Tejal Shah and Graham Morgan and Rajiv Ranjan},
doi = {10.1145/3561048},
issn = {1557-7341},
year = {2023},
date = {2023-09-30},
urldate = {2023-09-30},
journal = {ACM Comput. Surv.},
volume = {55},
number = {9},
pages = {1–33},
publisher = {Association for Computing Machinery (ACM)},
abstract = {<jats:p>As our dependence on intelligent machines continues to grow, so does the demand for more transparent and interpretable models. In addition, the ability to explain the model generally is now the gold standard for building trust and deployment of artificial intelligence systems in critical domains. Explainable artificial intelligence (XAI) aims to provide a suite of machine learning techniques that enable human users to understand, appropriately trust, and produce more explainable models. Selecting an appropriate approach for building an XAI-enabled application requires a clear understanding of the core ideas within XAI and the associated programming frameworks. We survey state-of-the-art programming techniques for XAI and present the different phases of XAI in a typical machine learning development process. We classify the various XAI approaches and, using this taxonomy, discuss the key differences among the existing XAI techniques. Furthermore, concrete examples are used to describe these techniques that are mapped to programming frameworks and software toolkits. It is the intention that this survey will help stakeholders in selecting the appropriate approaches, programming frameworks, and software toolkits by comparing them through the lens of the presented taxonomy.</jats:p>},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
<jats:p>As our dependence on intelligent machines continues to grow, so does the demand for more transparent and interpretable models. In addition, the ability to explain the model generally is now the gold standard for building trust and deployment of artificial intelligence systems in critical domains. Explainable artificial intelligence (XAI) aims to provide a suite of machine learning techniques that enable human users to understand, appropriately trust, and produce more explainable models. Selecting an appropriate approach for building an XAI-enabled application requires a clear understanding of the core ideas within XAI and the associated programming frameworks. We survey state-of-the-art programming techniques for XAI and present the different phases of XAI in a typical machine learning development process. We classify the various XAI approaches and, using this taxonomy, discuss the key differences among the existing XAI techniques. Furthermore, concrete examples are used to describe these techniques that are mapped to programming frameworks and software toolkits. It is the intention that this survey will help stakeholders in selecting the appropriate approaches, programming frameworks, and software toolkits by comparing them through the lens of the presented taxonomy.</jats:p>
Calder, Matthew; Ahmed, Mujeeb; Nagaraja, Shishir
SWaP: A Water Process Testbed for ICS Security Research Bachelor Thesis
2023.
@bachelorthesis{Calder2023,
title = {SWaP: A Water Process Testbed for ICS Security Research},
author = {Matthew Calder and Mujeeb Ahmed and Shishir Nagaraja},
doi = {10.1109/coins57856.2023.10189315},
year = {2023},
date = {2023-07-23},
urldate = {2023-07-23},
pages = {1–4},
publisher = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {bachelorthesis}
}
Dickinson, Carl; Nagaraja, Shishir; Ahmed, Chuadhry Mujeeb; Hyde, Richard
AGRITRUST: A Testbed to Enable Trustworthy Smart AgriTech Bachelor Thesis
2023.
@bachelorthesis{Dickinson2023,
title = {AGRITRUST: A Testbed to Enable Trustworthy Smart AgriTech},
author = {Carl Dickinson and Shishir Nagaraja and Chuadhry Mujeeb Ahmed and Richard Hyde},
doi = {10.1145/3597512.3600209},
year = {2023},
date = {2023-07-11},
urldate = {2023-07-11},
pages = {1–13},
publisher = {ACM},
keywords = {},
pubstate = {published},
tppubtype = {bachelorthesis}
}
Vaidya, Girish; Prabhakar, T. V.; Gnani, Nithish; Shah, Ryan; Nagaraja, Shishir
Sensor Identification via Acoustic Physically Unclonable Function Journal Article
In: Digital Threats, vol. 4, no. 2, pp. 1–25, 2023, ISSN: 2576-5337.
@article{Vaidya2022,
title = {Sensor Identification via Acoustic Physically Unclonable Function},
author = {Girish Vaidya and T. V. Prabhakar and Nithish Gnani and Ryan Shah and Shishir Nagaraja},
doi = {10.1145/3488306},
issn = {2576-5337},
year = {2023},
date = {2023-06-30},
urldate = {2023-06-30},
journal = {Digital Threats},
volume = {4},
number = {2},
pages = {1–25},
publisher = {Association for Computing Machinery (ACM)},
abstract = {<jats:p>
The traceability of components on a supply chain from a production facility to deployment and maintenance depends upon its irrefutable identity. There are two well-known identification methods: an identity code stored in the memory and embedding custom identification hardware. While storing the identity code is susceptible to malicious and unintentional attacks, the approach of embedding a custom identification hardware is infeasible for sensor nodes assembled with Commercially-Off-the-Shelf devices. We propose a novel identifier -
<jats:monospace>Acoustic PUF</jats:monospace>
based on the innate properties of the sensor node.
<jats:monospace>Acoustic PUF</jats:monospace>
combines the uniqueness component and the position component of the sensor device signature. The uniqueness component is derived by exploiting the manufacturing tolerances, thus making the signature unclonable. The position component is derived through acoustic fingerprinting, thus giving a sticky identity to the sensor device. We evaluate
<jats:monospace>Acoustic PUF</jats:monospace>
for Uniqueness, Repeatability, and Position identity with a deployment spanning several weeks. Through our experimental evaluation and further numerical analysis, we prove that
<jats:monospace>Acoustic PUF</jats:monospace>
can uniquely identify thousands of devices with 99% accuracy while simultaneously detecting the change in position. We use the physical position of a device within a synthetic sound-field both as an identity measure as well as to validate physical integrity of the device.
</jats:p>},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
<jats:p>
The traceability of components on a supply chain from a production facility to deployment and maintenance depends upon its irrefutable identity. There are two well-known identification methods: an identity code stored in the memory and embedding custom identification hardware. While storing the identity code is susceptible to malicious and unintentional attacks, the approach of embedding a custom identification hardware is infeasible for sensor nodes assembled with Commercially-Off-the-Shelf devices. We propose a novel identifier -
<jats:monospace>Acoustic PUF</jats:monospace>
based on the innate properties of the sensor node.
<jats:monospace>Acoustic PUF</jats:monospace>
combines the uniqueness component and the position component of the sensor device signature. The uniqueness component is derived by exploiting the manufacturing tolerances, thus making the signature unclonable. The position component is derived through acoustic fingerprinting, thus giving a sticky identity to the sensor device. We evaluate
<jats:monospace>Acoustic PUF</jats:monospace>
for Uniqueness, Repeatability, and Position identity with a deployment spanning several weeks. Through our experimental evaluation and further numerical analysis, we prove that
<jats:monospace>Acoustic PUF</jats:monospace>
can uniquely identify thousands of devices with 99% accuracy while simultaneously detecting the change in position. We use the physical position of a device within a synthetic sound-field both as an identity measure as well as to validate physical integrity of the device.
</jats:p>
The traceability of components on a supply chain from a production facility to deployment and maintenance depends upon its irrefutable identity. There are two well-known identification methods: an identity code stored in the memory and embedding custom identification hardware. While storing the identity code is susceptible to malicious and unintentional attacks, the approach of embedding a custom identification hardware is infeasible for sensor nodes assembled with Commercially-Off-the-Shelf devices. We propose a novel identifier -
<jats:monospace>Acoustic PUF</jats:monospace>
based on the innate properties of the sensor node.
<jats:monospace>Acoustic PUF</jats:monospace>
combines the uniqueness component and the position component of the sensor device signature. The uniqueness component is derived by exploiting the manufacturing tolerances, thus making the signature unclonable. The position component is derived through acoustic fingerprinting, thus giving a sticky identity to the sensor device. We evaluate
<jats:monospace>Acoustic PUF</jats:monospace>
for Uniqueness, Repeatability, and Position identity with a deployment spanning several weeks. Through our experimental evaluation and further numerical analysis, we prove that
<jats:monospace>Acoustic PUF</jats:monospace>
can uniquely identify thousands of devices with 99% accuracy while simultaneously detecting the change in position. We use the physical position of a device within a synthetic sound-field both as an identity measure as well as to validate physical integrity of the device.
</jats:p>
Xie, Xiang; Fernandez, Antonio Manuel Herrera; Shah, Tejal; Kassem, Mohamad; James, Philip
Learning partial correlation graph for multivariate sensor data and detecting sensor communities in smart buildings Journal Article
In: 2023.
@article{xie_herrerafernandez_shah_kassem_james_2023,
title = {Learning partial correlation graph for multivariate sensor data and detecting sensor communities in smart buildings},
author = {Xiang Xie and Antonio Manuel Herrera Fernandez and Tejal Shah and Mohamad Kassem and Philip James},
url = {https://www.repository.cam.ac.uk/handle/1810/350199},
doi = {10.17863/CAM.96862},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
publisher = {Apollo - University of Cambridge Repository},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Wang, Ping; Nagaraja, Shishir; Bourquard, Aurélien; Gao, Haichang; Yan, Jeff
SoK: Acoustic Side Channels Miscellaneous
2023.
@misc{wang2023sokacousticchannels,
title = {SoK: Acoustic Side Channels},
author = {Ping Wang and Shishir Nagaraja and Aurélien Bourquard and Haichang Gao and Jeff Yan},
url = {https://arxiv.org/abs/2308.03806},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Hackett, William; Trawicki, Stefan; Yu, Zhengxin; Suri, Neeraj; Garraghan, Peter
PINCH: An Adversarial Extraction Attack Framework for Deep Learning Models Miscellaneous
2023.
@misc{hackett2023pinchadversarialextractionattack,
title = {PINCH: An Adversarial Extraction Attack Framework for Deep Learning Models},
author = {William Hackett and Stefan Trawicki and Zhengxin Yu and Neeraj Suri and Peter Garraghan},
url = {https://arxiv.org/abs/2209.06300},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
2022
Ludvigsen, Kaspar Rosager; Nagaraja, Shishir; Daly, Angela
Preventing or Mitigating Adversarial Supply Chain Attacks Bachelor Thesis
2022.
@bachelorthesis{Ludvigsen2022b,
title = {Preventing or Mitigating Adversarial Supply Chain Attacks},
author = {Kaspar Rosager Ludvigsen and Shishir Nagaraja and Angela Daly},
doi = {10.1145/3560835.3564552},
year = {2022},
date = {2022-11-08},
urldate = {2022-11-08},
pages = {25–34},
publisher = {ACM},
keywords = {},
pubstate = {published},
tppubtype = {bachelorthesis}
}
Sun, Rui; Li, Yinhao; Shah, Tejal; Sham, Ringo W. H.; Szydlo, Tomasz; Qian, Bin; Thakker, Dhaval; Ranjan, Rajiv
FedMSA: A Model Selection and Adaptation System for Federated Learning Journal Article
In: Sensors, vol. 22, no. 19, 2022, ISSN: 1424-8220.
@article{Sun2022,
title = {FedMSA: A Model Selection and Adaptation System for Federated Learning},
author = {Rui Sun and Yinhao Li and Tejal Shah and Ringo W. H. Sham and Tomasz Szydlo and Bin Qian and Dhaval Thakker and Rajiv Ranjan},
doi = {10.3390/s22197244},
issn = {1424-8220},
year = {2022},
date = {2022-10-00},
urldate = {2022-10-00},
journal = {Sensors},
volume = {22},
number = {19},
publisher = {MDPI AG},
abstract = {<jats:p>Federated Learning (FL) enables multiple clients to train a shared model collaboratively without sharing any personal data. However, selecting a model and adapting it quickly to meet user expectations in a large-scale FL application with heterogeneous devices is challenging. In this paper, we propose a model selection and adaptation system for Federated Learning (FedMSA), which includes a hardware-aware model selection algorithm that trades-off model training efficiency and model performance base on FL developers’ expectation. Meanwhile, considering the expected model should be achieved by dynamic model adaptation, FedMSA supports full automation in building and deployment of the FL task to different hardware at scale. Experiments on benchmark and real-world datasets demonstrate the effectiveness of the model selection algorithm of FedMSA in real devices (e.g., Raspberry Pi and Jetson nano).</jats:p>},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
<jats:p>Federated Learning (FL) enables multiple clients to train a shared model collaboratively without sharing any personal data. However, selecting a model and adapting it quickly to meet user expectations in a large-scale FL application with heterogeneous devices is challenging. In this paper, we propose a model selection and adaptation system for Federated Learning (FedMSA), which includes a hardware-aware model selection algorithm that trades-off model training efficiency and model performance base on FL developers’ expectation. Meanwhile, considering the expected model should be achieved by dynamic model adaptation, FedMSA supports full automation in building and deployment of the FL task to different hardware at scale. Experiments on benchmark and real-world datasets demonstrate the effectiveness of the model selection algorithm of FedMSA in real devices (e.g., Raspberry Pi and Jetson nano).</jats:p>
Wei, Bo; Xu, Weitao; Li, Kai; Luo, Chengwen; Zhang, Jin
i^2 Key: A Cross-sensor Symmetric Key Generation System Using Inertial Measurements and Inaudible Sound Bachelor Thesis
2022.
@bachelorthesis{Wei2022,
title = {i^2 Key: A Cross-sensor Symmetric Key Generation System Using Inertial Measurements and Inaudible Sound},
author = {Bo Wei and Weitao Xu and Kai Li and Chengwen Luo and Jin Zhang},
doi = {10.1109/ipsn54338.2022.00022},
year = {2022},
date = {2022-05-00},
urldate = {2022-05-00},
pages = {183–194},
publisher = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {bachelorthesis}
}
Phengsuwan, Jedsada; Shah, Tejal; Sun, Rui; James, Philip; Thakker, Dhavalkumar; Ranjan, Rajiv
An ontology‐based system for discovering landslide‐induced emergencies in electrical grid Journal Article
In: Trans Emerging Tel Tech, vol. 33, no. 3, 2022, ISSN: 2161-3915.
@article{Phengsuwan2020,
title = {An ontology‐based system for discovering landslide‐induced emergencies in electrical grid},
author = {Jedsada Phengsuwan and Tejal Shah and Rui Sun and Philip James and Dhavalkumar Thakker and Rajiv Ranjan},
doi = {10.1002/ett.3899},
issn = {2161-3915},
year = {2022},
date = {2022-03-00},
urldate = {2022-03-00},
journal = {Trans Emerging Tel Tech},
volume = {33},
number = {3},
publisher = {Wiley},
abstract = {<jats:title>Summary</jats:title><jats:p>Early warning systems (EWS) for electrical grid infrastructure have played a significant role in the efficient management of electricity supply in natural hazard prone areas. Modern EWS rely on scientific methods to analyze a variety of Earth Observation and ancillary data provided by multiple and heterogeneous data sources for the monitoring of electrical grid infrastructure. Furthermore, through cooperation, EWS for natural hazards contribute to monitoring by reporting hazard events that are associated with a particular electrical grid network. Additionally, sophisticated domain knowledge of natural hazards and electrical grid is also required to enable dynamic and timely decision‐making about the management of electrical grid infrastructure in serious hazards. In this paper, we propose a data integration and analytics system that enables an interaction between natural hazard EWS and electrical grid EWS to contribute to electrical grid network monitoring and support decision‐making for electrical grid infrastructure management. We prototype the system using landslides as an example natural hazard for the grid infrastructure monitoring. Essentially, the system consists of background knowledge about landslides as well as information about data sources to facilitate the process of data integration and analysis. Using the knowledge modeled, the prototype system can report the occurrence of landslides and suggest potential data sources for the electrical grid network monitoring.</jats:p>},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
<jats:title>Summary</jats:title><jats:p>Early warning systems (EWS) for electrical grid infrastructure have played a significant role in the efficient management of electricity supply in natural hazard prone areas. Modern EWS rely on scientific methods to analyze a variety of Earth Observation and ancillary data provided by multiple and heterogeneous data sources for the monitoring of electrical grid infrastructure. Furthermore, through cooperation, EWS for natural hazards contribute to monitoring by reporting hazard events that are associated with a particular electrical grid network. Additionally, sophisticated domain knowledge of natural hazards and electrical grid is also required to enable dynamic and timely decision‐making about the management of electrical grid infrastructure in serious hazards. In this paper, we propose a data integration and analytics system that enables an interaction between natural hazard EWS and electrical grid EWS to contribute to electrical grid network monitoring and support decision‐making for electrical grid infrastructure management. We prototype the system using landslides as an example natural hazard for the grid infrastructure monitoring. Essentially, the system consists of background knowledge about landslides as well as information about data sources to facilitate the process of data integration and analysis. Using the knowledge modeled, the prototype system can report the occurrence of landslides and suggest potential data sources for the electrical grid network monitoring.</jats:p>
Phengsuwan, Jedsada; Shah, Tejal; Sun, Rui; James, Philip; Thakker, Dhavalkumar; Ranjan, Rajiv
An ontology‐based system for discovering landslide‐induced emergencies in electrical grid Journal Article
In: Trans Emerging Tel Tech, vol. 33, no. 3, 2022, ISSN: 2161-3915.
@article{Phengsuwan2020b,
title = {An ontology‐based system for discovering landslide‐induced emergencies in electrical grid},
author = {Jedsada Phengsuwan and Tejal Shah and Rui Sun and Philip James and Dhavalkumar Thakker and Rajiv Ranjan},
doi = {10.1002/ett.3899},
issn = {2161-3915},
year = {2022},
date = {2022-03-00},
urldate = {2022-03-00},
journal = {Trans Emerging Tel Tech},
volume = {33},
number = {3},
publisher = {Wiley},
abstract = {<jats:title>Summary</jats:title><jats:p>Early warning systems (EWS) for electrical grid infrastructure have played a significant role in the efficient management of electricity supply in natural hazard prone areas. Modern EWS rely on scientific methods to analyze a variety of Earth Observation and ancillary data provided by multiple and heterogeneous data sources for the monitoring of electrical grid infrastructure. Furthermore, through cooperation, EWS for natural hazards contribute to monitoring by reporting hazard events that are associated with a particular electrical grid network. Additionally, sophisticated domain knowledge of natural hazards and electrical grid is also required to enable dynamic and timely decision‐making about the management of electrical grid infrastructure in serious hazards. In this paper, we propose a data integration and analytics system that enables an interaction between natural hazard EWS and electrical grid EWS to contribute to electrical grid network monitoring and support decision‐making for electrical grid infrastructure management. We prototype the system using landslides as an example natural hazard for the grid infrastructure monitoring. Essentially, the system consists of background knowledge about landslides as well as information about data sources to facilitate the process of data integration and analysis. Using the knowledge modeled, the prototype system can report the occurrence of landslides and suggest potential data sources for the electrical grid network monitoring.</jats:p>},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
<jats:title>Summary</jats:title><jats:p>Early warning systems (EWS) for electrical grid infrastructure have played a significant role in the efficient management of electricity supply in natural hazard prone areas. Modern EWS rely on scientific methods to analyze a variety of Earth Observation and ancillary data provided by multiple and heterogeneous data sources for the monitoring of electrical grid infrastructure. Furthermore, through cooperation, EWS for natural hazards contribute to monitoring by reporting hazard events that are associated with a particular electrical grid network. Additionally, sophisticated domain knowledge of natural hazards and electrical grid is also required to enable dynamic and timely decision‐making about the management of electrical grid infrastructure in serious hazards. In this paper, we propose a data integration and analytics system that enables an interaction between natural hazard EWS and electrical grid EWS to contribute to electrical grid network monitoring and support decision‐making for electrical grid infrastructure management. We prototype the system using landslides as an example natural hazard for the grid infrastructure monitoring. Essentially, the system consists of background knowledge about landslides as well as information about data sources to facilitate the process of data integration and analysis. Using the knowledge modeled, the prototype system can report the occurrence of landslides and suggest potential data sources for the electrical grid network monitoring.</jats:p>
Shah, Ryan; Ahmed, Mujeeb; Nagaraja, Shishir
Fingerprinting Robot Movements via Acoustic Side Channel Miscellaneous
2022.
@misc{shah2022fingerprintingrobotmovementsacoustic,
title = {Fingerprinting Robot Movements via Acoustic Side Channel},
author = {Ryan Shah and Mujeeb Ahmed and Shishir Nagaraja},
url = {https://arxiv.org/abs/2209.10240},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Shah, Ryan; Ahmed, Mujeeb; Nagaraja, Shishir
Reconstructing Robot Operations via Radio-Frequency Side-Channel Miscellaneous
2022.
@misc{shah2022reconstructingrobotoperationsradiofrequency,
title = {Reconstructing Robot Operations via Radio-Frequency Side-Channel},
author = {Ryan Shah and Mujeeb Ahmed and Shishir Nagaraja},
url = {https://arxiv.org/abs/2209.10179},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Ludvigsen, Kaspar Rosager; Nagaraja, Shishir; Daly, Angela
The Dangers of Computational Law and Cybersecurity; Perspectives from Engineering and the AI Act Miscellaneous
2022.
@misc{ludvigsen2022dangerscomputationallawcybersecurity,
title = {The Dangers of Computational Law and Cybersecurity; Perspectives from Engineering and the AI Act},
author = {Kaspar Rosager Ludvigsen and Shishir Nagaraja and Angela Daly},
url = {https://arxiv.org/abs/2207.00295},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Ludvigsen, Kaspar Rosager; Nagaraja, Shishir
The Opportunity to Regulate Cybersecurity in the EU (and the World): Recommendations for the Cybersecurity Resilience Act Miscellaneous
2022.
@misc{ludvigsen2022opportunityregulatecybersecurityeu,
title = {The Opportunity to Regulate Cybersecurity in the EU (and the World): Recommendations for the Cybersecurity Resilience Act},
author = {Kaspar Rosager Ludvigsen and Shishir Nagaraja},
url = {https://arxiv.org/abs/2205.13196},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Ludvigsen, Kaspar Rosager; Nagaraja, Shishir; Daly, Angela
YASM (Yet Another Surveillance Mechanism) Miscellaneous
2022.
@misc{ludvigsen2022yasmyetsurveillancemechanism,
title = {YASM (Yet Another Surveillance Mechanism)},
author = {Kaspar Rosager Ludvigsen and Shishir Nagaraja and Angela Daly},
url = {https://arxiv.org/abs/2205.14601},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
2021
Taylor, Rhian; Ojha, Varun; Martino, Ivan; Nicosia, Giuseppe
Sensitivity Analysis for Deep Learning: Ranking Hyper-parameter Influence Bachelor Thesis
2021.
@bachelorthesis{Taylor2021b,
title = {Sensitivity Analysis for Deep Learning: Ranking Hyper-parameter Influence},
author = {Rhian Taylor and Varun Ojha and Ivan Martino and Giuseppe Nicosia},
doi = {10.1109/ictai52525.2021.00083},
year = {2021},
date = {2021-11-00},
urldate = {2021-11-00},
pages = {512–516},
publisher = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {bachelorthesis}
}
Xu, Weitao; Li, Zhenjiang; Xue, Wanli; Yu, Xiaotong; Wei, Bo; Wang, Jia; Luo, Chengwen; Li, Wei; Zomaya, Albert Y.
InaudibleKey Bachelor Thesis
2021.
@bachelorthesis{Xu2021,
title = {InaudibleKey},
author = {Weitao Xu and Zhenjiang Li and Wanli Xue and Xiaotong Yu and Bo Wei and Jia Wang and Chengwen Luo and Wei Li and Albert Y. Zomaya},
doi = {10.1145/3412382.3458260},
year = {2021},
date = {2021-05-18},
urldate = {2021-05-18},
pages = {106–118},
publisher = {ACM},
keywords = {},
pubstate = {published},
tppubtype = {bachelorthesis}
}
2020
Thakker, Dhavalkumar; Patel, Pankesh; Ali, Muhammad Intizar; Shah, Tejal
Semantic Web of Things for Industry 4.0 Journal Article
In: SW, vol. 11, no. 6, pp. 885–886, 2020, ISSN: 2210-4968.
@article{Thakker2020,
title = {Semantic Web of Things for Industry 4.0},
author = {Dhavalkumar Thakker and Pankesh Patel and Muhammad Intizar Ali and Tejal Shah},
editor = {Dhaval Thakker and Pankesh Patel and Muhammad Intizar Ali and Tejal Shah},
doi = {10.3233/sw-200407},
issn = {2210-4968},
year = {2020},
date = {2020-10-29},
urldate = {2020-10-29},
journal = {SW},
volume = {11},
number = {6},
pages = {885–886},
publisher = {SAGE Publications},
abstract = {<jats:p>Welcome to this special issue of the Semantic Web (SWJ) journal. The special issue compiles four technical contributions that significantly advance the state-of-the-art in Semantic Web of Things for Industry 4.0 including the use of Semantic Web technologies and techniques in Industry 4.0 solutions.</jats:p>},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
<jats:p>Welcome to this special issue of the Semantic Web (SWJ) journal. The special issue compiles four technical contributions that significantly advance the state-of-the-art in Semantic Web of Things for Industry 4.0 including the use of Semantic Web technologies and techniques in Industry 4.0 solutions.</jats:p>
2019
Gill, Sukhpal Singh; Tuli, Shreshth; Xu, Minxian; Singh, Inderpreet; Singh, Karan Vijay; Lindsay, Dominic; Tuli, Shikhar; Smirnova, Daria; Singh, Manmeet; Jain, Udit; Pervaiz, Haris; Sehgal, Bhanu; Kaila, Sukhwinder Singh; Misra, Sanjay; Aslanpour, Mohammad Sadegh; Mehta, Harshit; Stankovski, Vlado; Garraghan, Peter
Transformative effects of IoT, Blockchain and Artificial Intelligence on cloud computing: Evolution, vision, trends and open challenges Journal Article
In: Internet of Things, vol. 8, 2019, ISSN: 2542-6605.
@article{Gill2019,
title = {Transformative effects of IoT, Blockchain and Artificial Intelligence on cloud computing: Evolution, vision, trends and open challenges},
author = {Sukhpal Singh Gill and Shreshth Tuli and Minxian Xu and Inderpreet Singh and Karan Vijay Singh and Dominic Lindsay and Shikhar Tuli and Daria Smirnova and Manmeet Singh and Udit Jain and Haris Pervaiz and Bhanu Sehgal and Sukhwinder Singh Kaila and Sanjay Misra and Mohammad Sadegh Aslanpour and Harshit Mehta and Vlado Stankovski and Peter Garraghan},
doi = {10.1016/j.iot.2019.100118},
issn = {2542-6605},
year = {2019},
date = {2019-12-00},
urldate = {2019-12-00},
journal = {Internet of Things},
volume = {8},
publisher = {Elsevier BV},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Phengsuwan, Jedsada; Thekkummal, Nipun Balan; Shah, Teja; James, Philip; Thakker, Dhavalkumar; Sun, Rui; Pullarkatt, Divya; Hemalatha, T.; Ramesh, Maneesha Vinodini; Ranjan, Rajiv
Context-Based Knowledge Discovery and Querying for Social Media Data Bachelor Thesis
2019.
@bachelorthesis{Phengsuwan2019,
title = {Context-Based Knowledge Discovery and Querying for Social Media Data},
author = {Jedsada Phengsuwan and Nipun Balan Thekkummal and Teja Shah and Philip James and Dhavalkumar Thakker and Rui Sun and Divya Pullarkatt and T. Hemalatha and Maneesha Vinodini Ramesh and Rajiv Ranjan},
doi = {10.1109/iri.2019.00056},
year = {2019},
date = {2019-07-00},
urldate = {2019-07-00},
pages = {307–314},
publisher = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {bachelorthesis}
}