PUBLICATIONS
Preprints
F. Jiang, Z. Xu, L. Niu, Z. Xiang, B. Ramasubramanian, B. Li, R. Poovendran, ArtPrompt: ASCII Art-Based Jailbreak Attacks against Aligned LLMs, Preprint, 2024. [arXiv] [Media Features: ArsTechnica, Inc.com, PCGamer, Tom's Hardware, VentureBeat, Twitter]
D. Sahabandu, X. Xu, A. Rajabi, L. Niu, B. Ramasubramanian, B. Li, R. Poovendran, Game of Trojans: Adaptive Adversaries against Output-based Trojaned Model Detectors, Preprint, 2024. [arXiv]
A. Rajabi, R. Pimple, A. Janardhanan, S. Asokraj, B. Ramasubramanian, R. Poovendran, Double-Dip: Thwarting Label-Only Membership Inference Attacks with Transfer Learning and Randomization, Preprint, 2024. [arXiv]
B. Xiao, B. Ramasubramanian, R. Poovendran, Shaping Advice in Deep Reinforcement Learning, Preprint, 2022. [arXiv] [Preliminary Version]
A. Rajabi, B. Ramasubramanian, R. Poovendran, Trojan Horse Training for Breaking Defenses Against Backdoor Attacks, Preprint, 2022. [arXiv]
D. Sahabandu, A. Rajabi, L. Niu, B. Li, B. Ramasubramanian, R. Poovendran, Game of Trojans: A Submodular Byzantine Approach, Preprint, 2022. [arXiv]
Journal
L. Niu, B. Ramasubramanian, A. Clark, R. Poovendran, Robust Satisfaction of Metric Interval Temporal Logic Objectives in Adversarial Environments, MDPI Games, Special Issue on Game-Theoretic Analysis of Network Security and Privacy (Ed.: Prof. Y. Vorobeychik), Vol. 14, Issue 2, April 2023 . (DOI: https://doi.org/10.3390/g14020030). [COVER PAGE Feature]
B. Ramasubramanian, M. A. Rajan, M. G. Chandra, R. Cleaveland, S. I. Marcus, Resilience to Denial-of-Service Attacks : A Structured Systems Approach, European Journal on Control, Vol. 63, pp. 61-69, January 2022 (DOI: https://doi.org/10.1016/j.ejcon.2021.09.005). [arXiv]
B. Ramasubramanian, L. Niu, A. Clark, L. Bushnell, R. Poovendran, Secure Control in Partially Observable Environments to Satisfy LTL Specifications, IEEE Transactions on Automatic Control, Vol. 66, No. 12, pp. 5665-5679, 2021 (DOI: 10.1109/TAC.2020.3039484). [arXiv]
B. Ramasubramanian, R. Cleaveland, S. I. Marcus, Notions of Centralized and Decentralized Opacity in Linear Systems, IEEE Transactions on Automatic Control, Vol. 65, No. 4, pp. 1442-1455, 2020 (DOI: 10.1109/TAC.2019.2920837). [arXiv]
Conference
Q. Lu, B. Ramasubramanian, R. Poovendran, EDC: Effective and Efficient Dialog Comprehension for Dialog State Tracking, Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2024. [Preprint] [Acceptance rate ~23%]
A. Al Maruf, L. Niu, B. Ramasubramanian, A. Clark, R. Poovendran, Risk-Aware Distributed Multi-Agent Reinforcement Learning, Proceedings of the American Control Conference (ACC), 2024. [arXiv]
Z. Xiang, F. Jiang, Z. Xiong, B. Ramasubramanian, R. Poovendran, B. Li, BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models, International Conference on Learning Representations (ICLR), 2024. [arXiv] [Acceptance rate ~31%]
K. Balasubramanian, A. Gowda Baragur, D. Donadel, D. Sahabandu, A. Brighente, B. Ramasubramanian, M. Conti, R. Poovendran, CANLP: NLP-Based Intrusion Detection System for CAN, ACM Symposium on Applied Computing (SAC), Cyber Physical Systems Track, 2024.
J. Jia, Z. Yuan, D. Sahabandu, L. Niu, A. Rajabi, B. Ramasubramanian, B. Li, R. Poovendran, FedGame: A Game-Theoretic Defense Against Backdoor Attacks in Federated Learning, Conference on Advances in Neural Information Processing Systems (NeurIPS), 2023. [Paper] [Acceptance rate ~26%]
A. Rajabi, S. Asokraj, F. Jiang, L. Niu, B. Ramasubramanian, J. Ritcey, R. Poovendran, MDTD: A Multi-Domain Trojan Detector for Deep Neural Networks, ACM Conference on Computer and Communications Security (CCS), 2023. [Paper] [arXiv] [Acceptance rate ~20%]
A. Al Maruf, L. Niu, B. Ramasubramanian, A. Clark, R. Poovendran, Learning Dissemination Strategies for External Sources in Opinion Dynamic Models with Cognitive Biases, International Joint Conference on Artificial Intelligence (IJCAI), 2023. [Paper] [Preprint] [Acceptance rate ~15%]
D. Danis, P. Parmacek, D. Dunajsky, B. Ramasubramanian, Multi-Agent Reinforcement Learning with Prospect Theory, Proceedings of the SIAM Conference on Control and its Applications (SIAM CT), 2023. [Paper]
A. Rajabi, D. Sahabandu, L. Niu, B. Ramasubramanian, R. Poovendran, LDL: A Defense for Label-Based Membership Inference Attacks, ACM ASIA Conference on Computer and Communications Security (AsiaCCS), 2023. [Paper] [arXiv] [Acceptance rate ~17%]
A. Lotto, V. Singh, B. Ramasubramanian, A. Brighente, M. Conti, R. Poovendran, BARON: Base-Station Authentication Through Core Network for Mobility Management in 5G Networks, ACM Conference on Security and Privacy in Wireless and Mobile Networks (WiSec), 2023. [Paper][Video] [Oral Presentation; Acceptance rate 25%]
A. Al Maruf, L. Niu, B. Ramasubramanian, A. Clark, R. Poovendran, Cognitive Bias-Aware Dissemination Strategies for Opinion Dynamics with External Information Sources, International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), 2023. [Paper] [Poster Presentation; Acceptance rate ~22%]
A. Rajabi, B. Ramasubramanian, A. Al Maruf, R. Poovendran, Privacy-Preserving Reinforcement Learning Beyond Expectation, Proceedings of the IEEE Conference on Decision and Control (CDC), 2022. [Paper] [arXiv]
B. Xiao, B. Ramasubramanian, R. Poovendran, Agent-Temporal Attention for Reward Redistribution in Episodic Multi-Agent Reinforcement Learning, International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), 2022. [Paper] [arXiv] [Oral Presentation; Acceptance rate 26%]
B. Ramasubramanian, L. Niu, A. Clark, R. Poovendran, Reinforcement Learning Beyond Expectation, Proceedings of the IEEE Conference on Decision and Control, 2021. [Paper] [arXiv]
B. Ramasubramanian, B. Xiao, L. Bushnell, R. Poovendran, Safety-Critical Online Control with Adversarial Disturbances, Proceedings of the IEEE Conference on Decision and Control, 2020. [Paper] [arXiv]
B. Ramasubramanian, L. Niu, A. Clark, L. Bushnell, R. Poovendran, Privacy-Preserving Resilience of Cyber-Physical Systems to Adversaries, Proceedings of the IEEE Conference on Decision and Control, 2020. [Paper] [arXiv]
B. Xiao, Q. Lu, B. Ramasubramanian, A. Clark, L. Bushnell, R. Poovendran, FRESH: Interactive Reward Shaping in High-dimensional State Spaces Using Human Feedback, International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), 2020. [Paper] [arXiv] [Video] [Oral Presentation; Acceptance rate 25%]
L. Niu, B. Ramasubramanian, A. Clark, L. Bushnell, R. Poovendran, Control Synthesis for Cyber-Physical Systems to Satisfy Metric Interval Temporal Logic Objectives under Timing and Actuator Attacks, Proceedings of the International Conference on Cyber-physical Systems (ICCPS), 2020. [Paper] [arXiv] [Video] [Acceptance rate 25%] [BEST PAPER FINALIST - ACM SIGBED Blog Announcement]
B. Xiao, B. Ramasubramanian, A. Clark, H. Hajishirzi, L. Bushnell, R. Poovendran, Potential-Based Advice for Stochastic Policy Learning, Proceedings of the IEEE Conference on Decision and Control, 2019. [Paper] [arXiv]
B. Ramasubramanian, L. Niu, A. Clark, L. Bushnell, R. Poovendran, Linear Temporal Logic Satisfaction in Adversarial Environments using Secure Control Barrier Certificates, International Conference on Decision and Game Theory for Security, Lecture Notes in Computer Science, Springer, 2019. [Paper] [arXiv]
B. Ramasubramanian, A. Clark, L. Bushnell, R. Poovendran, Secure Control under Partial Observability with Temporal Logic Constraints, Proceedings of the American Control Conference, 2019. [Paper] [arXiv]
B. Ramasubramanian, R. Cleaveland, S. I. Marcus, Opacity for Switched Linear Systems: Notions and Characterization, Proceedings of the IEEE Conference on Decision and Control, 2017. [Paper]
B. Ramasubramanian, R. Cleaveland, S. I. Marcus, A Framework for Decentralized Opacity in Linear Systems, Proceedings of the Annual Allerton Conference in Communication, Control, and Computing, 2016. [Paper]
B. Ramasubramanian, R. Cleaveland, S. I. Marcus, A Framework for Opacity in Linear Systems, Proceedings of the American Control Conference, 2016. [Paper]
B. Ramasubramanian, M. A. Rajan, M. G. Chandra, Structural Resilience of Cyberphysical Systems Under Attack, Proceedings of the American Control Conference, 2016. [Paper]
V. S. Mai*, D. Maity*, B. Ramasubramanian*, M. C. Rotkowitz, Convex Methods for Rank Constrained Optimization Problems, Proceedings of the SIAM Conference on Control and its Applications, 2015. [Paper](* - equal contributors)
B. Ramasubramanian, S. R. Khare, M. N. Belur, Generic Degree Structure of the Minimal Polynomial Nullspace Basis: A Block Toeplitz Matrix Approach, Proceedings of the IEEE Indian Control Conference, 2015. [Slides] [Paper]
Workshop
F. Jiang, Z. Xu, L. Niu, Z. Xiang, B. Ramasubramanian, B. Li, R. Poovendran, ArtPrompt: ASCII Art-Based Jailbreak Attacks against Aligned LLMs, ICLR 2024 Workshop on Secure and Trustworthy Large Language Models (SetLLM). [Paper]
Z. Xiang, F. Jiang, Z. Xiong, B. Ramasubramanian, R. Poovendran, B. Li, BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models, NeurIPS 2023 Workshop on Backdoors in Deep Learning- The Good, The Bad, and The Ugly. [Paper][Oral Presentation]
Posters and Presentations
A. Rajabi, R. Pimple, A. Janardhanan, S. Asokraj, B. Ramasubramanian, R. Poovendran, POSTER: Double-Dip: Thwarting Label-Only Membership Inference Attacks with Transfer Learning and Randomization, ACM ASIA Conference on Computer and Communications Security (AsiaCCS), 2024.
D. Sahabandu, X. Xu, A. Rajabi, L. Niu, B. Ramasubramanian, B. Li, R. Poovendran, POSTER: Game of Trojans: Adaptive Adversaries against Output-based Trojaned Model Detectors, ACM ASIA Conference on Computer and Communications Security (AsiaCCS), 2024.
T. Roque, M. Le, D. Danis, B. Ramasubramanian, Risk-Aware Decision Making for Autonomous Driving with Theory of Mind, Lecture Presentation at the SIAM Conference on Control and its Applications (SIAM CT), 2023.
D. Danis, P. Parmacek, D. Dunajsky, B. Ramasubramanian, Multi-Agent Reinforcement Learning with Prospect Theory, Lecture Presentation at the SIAM Conference on Control and its Applications (SIAM CT), 2023.
B. Ramasubramanian, Cognizant Learning for Autonomous Cyber Physical Systems, NSF CPS PI Meeting, 2022. [Poster] [Video]
B. Ramasubramanian, L. Bushnell, R. Poovendran, A. Clark, S.I. Marcus, R. Cleaveland, Secure Cyber-Physical Systems in Partially Observable Environments: Perspectives from Control Theory and Formal Methods, Western USA ECE Departments Heads Association (WECEDHA), 2018, Conference on Decision and Control (CDC), 2018, and UW ECE Research Review Day. [Poster]
B. Ramasubramanian, M. A. Rajan, M. G. Chandra, Structural Resilience of Cyberphysical Systems Under Attack, Research in Attacks, Intrusions, and Defenses (RAID), 2015. [Poster]
J. Ferlez, B. Ramasubramanian, R. Cleaveland, S. I. Marcus, Cyberphysical Systems: Compositionality and Opacity, Institute for Systems Research Annual Event, 2017. [Poster]
Thesis
Opacity and Structural Resilience in Cyberphysical Systems [Slides] [Dissertation]