| Qu-ANTI-zation: Exploiting Quantization Artifacts for Achieving Adversarial Outcomes S Hong, MA Panaitescu-Liess, Y Kaya, T Dumitras Advances in Neural Information Processing Systems 34, 9303-9316, 2021 | 19 | 2021 |
| More Context, Less Distraction: Zero-shot Visual Classification by Inferring and Conditioning on Contextual Attributes B An, S Zhu, MA Panaitescu-Liess, CK Mummadi, F Huang The Twelfth International Conference on Learning Representations, 2024 | 18* | 2024 |
| Self-supervised representation learning on document images A Cosma, M Ghidoveanu, M Panaitescu-Liess, M Popescu Document Analysis Systems: 14th IAPR International Workshop, DAS 2020, Wuhan …, 2020 | 16 | 2020 |
| Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models B An, S Zhu, R Zhang, MA Panaitescu-Liess, Y Xu, F Huang arXiv preprint arXiv:2409.00598, 2024 | 9 | 2024 |
| Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data? MA Panaitescu-Liess, Z Che, B An, Y Xu, P Pathmanathan, S Chakraborty, ... arXiv preprint arXiv:2407.17417, 2024 | 4 | 2024 |
| AdvBDGen: Adversarially Fortified Prompt-Specific Fuzzy Backdoor Generator Against LLM Alignment P Pathmanathan, UM Sehwag, MA Panaitescu-Liess, F Huang arXiv preprint arXiv:2410.11283, 2024 | | 2024 |
| Like Oil and Water: Group Robustness Methods and Poisoning Defenses Don’t Mix MA Panaitescu-Liess, Y Kaya, S Zhu, F Huang, T Dumitras The Twelfth International Conference on Learning Representations, 2024 | | 2024 |
| PoisonedParrot: Subtle Data Poisoning Attacks to Elicit Copyright-Infringing Content from Large Language Models MA Panaitescu-Liess, P Pathmanathan, Y Kaya, Z Che, B An, S Zhu, ... Neurips Safe Generative AI Workshop 2024, 0 | | |
