| Maze: Data-free model stealing attack using zeroth-order gradient estimation S Kariyappa, A Prakash, MK Qureshi Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2021 | 209 | 2021 |
| Improving adversarial robustness of ensembles with diversity training S Kariyappa, MK Qureshi arXiv preprint arXiv:1901.09981, 2019 | 164 | 2019 |
| Defending against model stealing attacks with adaptive misinformation S Kariyappa, MK Qureshi Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2020 | 143 | 2020 |
| Reducing the impact of phase-change memory conductance drift on the inference of large-scale hardware neural networks S Ambrogio, M Gallot, K Spoon, H Tsai, C Mackin, M Wesson, ... 2019 IEEE International Electron Devices Meeting (IEDM), 6.1. 1-6.1. 4, 2019 | 70 | 2019 |
| 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 | 44 | 2023 |
| Enabling transparent memory-compression for commodity memory systems V Young, S Kariyappa, MK Qureshi 2019 IEEE International Symposium on High Performance Computer Architecture …, 2019 | 43* | 2019 |
| Exploit: Extracting private labels in split learning S Kariyappa, MK Qureshi 2023 IEEE conference on secure and trustworthy machine learning (SaTML), 165-175, 2023 | 42* | 2023 |
| Noise-resilient DNN: Tolerating noise in PCM-based AI accelerators via noise-aware training S Kariyappa, H Tsai, K Spoon, S Ambrogio, P Narayanan, C Mackin, ... IEEE Transactions on Electron Devices 68 (9), 4356-4362, 2021 | 41 | 2021 |
| Protecting dnns from theft using an ensemble of diverse models S Kariyappa, A Prakash, MK Qureshi International Conference on Learning Representations, 2021 | 38 | 2021 |
| Bespoke cache enclaves: Fine-grained and scalable isolation from cache side-channels via flexible set-partitioning G Saileshwar, S Kariyappa, M Qureshi 2021 International Symposium on Secure and Private Execution Environment …, 2021 | 35 | 2021 |
| 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, 51904-51925, 2023 | 13 | 2023 |
| Measuring and controlling split layer privacy leakage using fisher information K Maeng, C Guo, S Kariyappa, E Suh arXiv preprint arXiv:2209.10119, 2022 | 10 | 2022 |
| Enabling inference privacy with adaptive noise injection S Kariyappa, O Dia, MK Qureshi arXiv preprint arXiv:2104.02261, 2021 | 8 | 2021 |
| 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 | 6 | 2024 |
| Privacy-preserving algorithmic recourse S Pentyala, S Sharma, S Kariyappa, F Lecue, D Magazzeni arXiv preprint arXiv:2311.14137, 2023 | 6 | 2023 |
| SHAP@ k: efficient and probably approximately correct (PAC) identification of top-k features S Kariyappa, L Tsepenekas, F Lécué, D Magazzeni Proceedings of the AAAI Conference on Artificial Intelligence 38 (12), 13068 …, 2024 | 5 | 2024 |
| Interpretable llm-based table question answering G Nguyen, I Brugere, S Sharma, S Kariyappa, AT Nguyen, F Lecue arXiv preprint arXiv:2412.12386, 2024 | 3 | 2024 |
| Drift regularization to counteract variation in drift coefficients for analog accelerators H Tsai, S Kariyappa US Patent 11,514,326, 2022 | 3 | 2022 |
| Neural network accelerators resilient to conductance drift H Tsai, S Ambrogio, S Kariyappa, M Gallot US Patent 12,229,680, 2025 | 2 | 2025 |
| Progressive inference: explaining decoder-only sequence classification models using intermediate predictions S Kariyappa, F Lécué, S Mishra, C Pond, D Magazzeni, M Veloso arXiv preprint arXiv:2406.02625, 2024 | 1 | 2024 |
Moinuddin QureshiProfessor, Georgia Institute of TechnologyVerified email at gatech.edu