| FATH: Authentication-based Test-time Defense against Indirect Prompt Injection Attacks J Wang, F Wu, W Li, J Pan, E Suh, ZM Mao, M Chen, C Xiao arXiv preprint arXiv:2410.21492, 2024 | | 2024 |
| Autodan-turbo: A lifelong agent for strategy self-exploration to jailbreak llms X Liu, P Li, E Suh, Y Vorobeychik, Z Mao, S Jha, P McDaniel, H Sun, B Li, ... arXiv preprint arXiv:2410.05295, 2024 | 2 | 2024 |
| Remote Power Side-Channel Attacks on FPGAs M Zhao, GE Suh IEEE Design & Test, 2024 | | 2024 |
| Accelerating ReLU for MPC-Based Private Inference with a Communication-Efficient Sign Estimation K Maeng, GE Suh Proceedings of Machine Learning and Systems 6, 128-147, 2024 | | 2024 |
| LazyDP: Co-Designing Algorithm-Software for Scalable Training of Differentially Private Recommendation Models J Lim, Y Kwon, R Hwang, K Maeng, E Suh, M Rhu Proceedings of the 29th ACM International Conference on Architectural …, 2024 | | 2024 |
| LibPreemptible: Enabling Fast, Adaptive, and Hardware-Assisted User-Space Scheduling Y Li, N Lazarev, D Koufaty, T Yin, A Anderson, Z Zhang, GE Suh, K Kaffes, ... 2024 IEEE International Symposium on High-Performance Computer Architecture …, 2024 | | 2024 |
| Bounding the invertibility of privacy-preserving instance encoding using fisher information K Maeng, C Guo, S Kariyappa, GE Suh Advances in Neural Information Processing Systems 36, 2024 | 4 | 2024 |
| Formal Privacy Proof of Heuristic Obfuscation: The Possibility and Impossibility of Learnable Obfuscation H Xiao, GE Suh, S Devadas | | 2024 |
| Information flow control in machine learning through modular model architecture T Tiwari, S Gururangan, C Guo, W Hua, S Kariyappa, U Gupta, W Xiong, ... 33rd USENIX Security Symposium (USENIX Security 24), 6921-6938, 2024 | 5 | 2024 |
| SpecVerilog: Adapting Information Flow Control for Secure Speculation D Zagieboylo, C Sherk, AC Myers, GE Suh Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications …, 2023 | 1 | 2023 |
| Base and compressed difference data deduplication P Sungbo, GE Suh US Patent 11,797,207, 2023 | 3 | 2023 |
| Approximating ReLU on a Reduced Ring for Efficient MPC-based Private Inference K Maeng, GE Suh arXiv preprint arXiv:2309.04875, 2023 | | 2023 |
| Towards fast, adaptive, and hardware-assisted user-space scheduling N Lazarev, D Koufaty, Y Yin, A Anderson, Z Zhang, E Suh, K Kaffes, ... arXiv preprint arXiv:2308.02896, 2023 | 1 | 2023 |
| Cocktail party attack: Breaking aggregation-based privacy in federated learning using independent component analysis S Kariyappa, C Guo, K Maeng, W Xiong, GE Suh, MK Qureshi, HHS Lee International Conference on Machine Learning, 15884-15899, 2023 | 25 | 2023 |
| Autocat: Reinforcement learning for automated exploration of cache-timing attacks M Luo, W Xiong, G Lee, Y Li, X Yang, A Zhang, Y Tian, HHS Lee, GE Suh 2023 IEEE International Symposium on High-Performance Computer Architecture …, 2023 | 12 | 2023 |
| Macta: A multi-agent reinforcement learning approach for cache timing attacks and detection J Cui, X Yang ICLR 2023, 2023 | 5 | 2023 |
| Gpu-based private information retrieval for on-device machine learning inference M Lam, J Johnson, W Xiong, K Maeng, U Gupta, Y Li, L Lai, I Leontiadis, ... arXiv preprint arXiv:2301.10904, 2023 | 6 | 2023 |
| Mitigating Metastable Failures in Distributed Systems with Offline Reinforcement Learning Y Li, D Zha, T Zhang, GE Suh, C Delimitrou, FY Yan | | 2023 |
| Strong asymptotic composition theorems for mutual information measures B Wu, AB Wagner, I Issa, GE Suh IEEE Transactions on Information Theory, 2022 | 4 | 2022 |
| Data leakage via access patterns of sparse features in deep learning-based recommendation systems H Hashemi, W Xiong, L Ke, K Maeng, M Annavaram, GE Suh, HHS Lee arXiv preprint arXiv:2212.06264, 2022 | 4 | 2022 |
Srinivas DevadasEdwin Sibley Webster Professor of Electrical Engineering and Computer Science, MITVerified email at mit.edu
