Michael-Andrei Panaitescu-Liess

According to our database, Michael-Andrei Panaitescu-Liess authored at least 7 papers between 2021 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2024

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

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

CoRR, 2024

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

Bang An, Sicheng Zhu, Ruiyi Zhang, Michael-Andrei Panaitescu-Liess, Yuancheng Xu, Furong Huang

CoRR, 2024

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

Michael-Andrei Panaitescu-Liess, Zora Che, Bang An, Yuancheng Xu, Pankayaraj Pathmanathan, Souradip Chakraborty, Sicheng Zhu, Tom Goldstein, Furong Huang

CoRR, 2024

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

Michael-Andrei Panaitescu-Liess, Yigitcan Kaya, Sicheng Zhu, Furong Huang, Tudor Dumitras

Proceedings of the Twelfth International Conference on Learning Representations, 2024

PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts.

Bang An, Sicheng Zhu, Michael-Andrei Panaitescu-Liess, Chaithanya Kumar Mummadi, Furong Huang

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

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

Bang An, Sicheng Zhu, Michael-Andrei Panaitescu-Liess, Chaithanya Kumar Mummadi, Furong Huang

CoRR, 2023

2021

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

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

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021