| Stealing the decoding algorithms of language models A Naseh, K Krishna, M Iyyer, A Houmansadr Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications …, 2023 | 6 | 2023 |
| On the risks of stealing the decoding algorithms of language models A Naseh, K Krishna, M Iyyer, A Houmansadr arXiv preprint arXiv:2303.04729, 2023 | 5 | 2023 |
| Iteratively Prompting Multimodal LLMs to Reproduce Natural and AI-Generated Images A Naseh, K Thai, M Iyyer, A Houmansadr arXiv preprint arXiv:2404.13784, 2024 | 2 | 2024 |
| Understanding (un) intended memorization in text-to-image generative models A Naseh, J Roh, A Houmansadr arXiv preprint arXiv:2312.07550, 2023 | 2 | 2023 |
| Memory Triggers: Unveiling Memorization in Text-To-Image Generative Models through Word-Level Duplication A Naseh, J Roh, A Houmansadr AAAI Workshop on Privacy-Preserving Artificial Intelligence (PPAI), 2023 | 2 | 2023 |
| Injecting Bias in Text-To-Image Models via Composite-Trigger Backdoors A Naseh, J Roh, E Bagdasaryan, A Houmansadr arXiv preprint arXiv:2406.15213, 2024 | | 2024 |
| Diffence: Fencing Membership Privacy With Diffusion Models Y Peng, A Naseh, A Houmansadr arXiv preprint arXiv:2312.04692, 2023 | | 2023 |
Amir HoumansadrUniversity of Massachusetts Amherst在 cs.umass.edu 的电子邮件经过验证
