To ChatGPT, or not to ChatGPT: That is the question! A Pegoraro, K Kumari, H Fereidooni, AR Sadeghi arXiv preprint arXiv:2304.01487, 2023 | 51 | 2023 |
BayBFed: Bayesian Backdoor Defense for Federated Learning K Kumari, P Rieger, H Fereidooni, M Jadliwala, AR Sadeghi IEEE Symposium on Security and Privacy (SP), 737-754, 2023 | 17 | 2023 |
Demasq: Unmasking the chatgpt wordsmith K Kumari, A Pegoraro, H Fereidooni, AR Sadeghi arXiv preprint arXiv:2311.05019, 2023 | 4 | 2023 |
Analyzing Defense Strategies Against Mobile Information Leakages: A Game-Theoretic Approach K Kumari, M Jadliwala, A Maiti, MH Manshaei International Conference on Decision and Game Theory for Security, 276-296, 2019 | 3 | 2019 |
Towards a Game-theoretic Understanding of Explanation-based Membership Inference Attacks K Kumari, M Jadliwala, SK Jha, A Maiti arXiv preprint arXiv:2404.07139, 2024 | | 2024 |
DeepEclipse: How to Break White-Box DNN-Watermarking Schemes A Pegoraro, C Segna, K Kumari, AR Sadeghi arXiv preprint arXiv:2403.03590, 2024 | | 2024 |