Michael-Andrei Panaitescu-Liess

Most-cited papers

1. Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models

   Bang An, Sicheng Zhu, Rui-Yi Zhang, Michael-Andrei Panaitescu-Liess +2 more

   2024arXiv.org44 citations

   Semantic Scholar

   Save

2. Qu-ANTI-zation: Exploiting Quantization Artifacts for Achieving Adversarial Outcomes

   Sanghyun Hong, Michael-Andrei Panaitescu-Liess, Yiğitcan Kaya, Tudor Dumitras

   2021Neural Information Processing Systems33 citations

   Semantic Scholar

   Save

3. Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?

   Michael-Andrei Panaitescu-Liess, Zora Che, Bang An, Yuancheng Xu +5 more

   2024AAAI Conference on Artificial Intelligence28 citations

   Semantic Scholar

   Save

4. PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts

   Bang An, Sicheng Zhu, Michael-Andrei Panaitescu-Liess, Chaithanya Kumar Mummadi +1 more

   2023International Conference on Learning Representations22 citations

   Semantic Scholar

   Save

5. More Context, Less Distraction: Visual Classification by Inferring and Conditioning on Contextual Attributes

   Bang An, Sicheng Zhu, Michael-Andrei Panaitescu-Liess, Chaithanya Kumar Mummadi +1 more

   2023arXiv.org15 citations Open access

   Semantic Scholar

   Save

6. Self-Supervised Representation Learning on Document Images

   Adrian Cosma, Mihai Ghidoveanu, Michael-Andrei Panaitescu-Liess, M. Popescu

   2020International Workshop on Document Analysis Systems15 citations Open access

   Semantic Scholar

   Save

7. RAGPart & RAGMask: Retrieval-Stage Defenses Against Corpus Poisoning in Retrieval-Augmented Generation

   Pankayaraj Pathmanathan, Michael-Andrei Panaitescu-Liess, Cho-Yu Jason Chiang, Furong Huang

   2025arXiv.org7 citations

   Semantic Scholar

   Save

8. AdvBDGen: Adversarially Fortified Prompt-Specific Fuzzy Backdoor Generator Against LLM Alignment

   Pankayaraj Pathmanathan, Udari Madhushani Sehwag, Michael-Andrei Panaitescu-Liess, Furong Huang

   2024arXiv.org6 citations

   Semantic Scholar

   Save

9. PoisonedParrot: Subtle Data Poisoning Attacks to Elicit Copyright-Infringing Content from Large Language Models

   Michael-Andrei Panaitescu-Liess, Pankayaraj Pathmanathan, Yiğitcan Kaya, Zora Che +4 more

   2025North American Chapter of the Association for Computational Linguistics3 citations

   Semantic Scholar

   Save

10. More Context, Less Distraction: Improving Zero-Shot Inference of CLIP by Inferring and Describing Spurious Features

    Bang An, Sicheng Zhu, Michael-Andrei Panaitescu-Liess, Chaithanya Kumar Mummadi +1 more

    3 citations

    Semantic Scholar

    Save

11. AdvBDGen: A Robust Framework for Generating Adaptive and Stealthy Backdoors in LLM Alignment

    Pankayaraj Pathmanathan, Udari Madhushani Sehwag, Michael-Andrei Panaitescu-Liess, Cho-Yu Jason Chiang +1 more

    2026AAAI Conference on Artificial Intelligence1 citations Open access

    Semantic Scholar

    Save

12. Compositional Adversarial Training for Robust Visual Watermarking

    Anirudh Satheesh, Michael-Andrei Panaitescu-Liess, An Xu, Georgios Milis +3 more

    2026arXiv.org1 citations

    Semantic Scholar

    Save

13. Like Oil and Water: Group Robustness Methods and Poisoning Defenses May Be at Odds

    Michael-Andrei Panaitescu-Liess, Yiğitcan Kaya, Sicheng Zhu, Furong Huang +1 more

    2025International Conference on Learning Representations0 citations

    Semantic Scholar

    Save

14. Like Oil and Water: Group Robustness and Poisoning Defenses Don’t Mix

    Michael-Andrei Panaitescu-Liess, Git-Can-Ka-Ya Yi, Tudor Dumitras

    0 citations

    Semantic Scholar

    Save