Panaitescu-Liess, Michael-Andrei

12 publications

ICLRW 2025 AdvBDGen: A Robust Framework for Generating Adaptive and Stealthy Backdoors in LLM Alignment Attacks Pankayaraj Pathmanathan, Udari Madhushani Sehwag, Michael-Andrei Panaitescu-Liess, Furong Huang

AAAI 2025 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

NeurIPSW 2024 AdvBDGen: Adversarially Fortified Prompt-Specific Fuzzy Backdoor Generator Against LLM Alignment Pankayaraj Pathmanathan, Udari Madhushani Sehwag, Michael-Andrei Panaitescu-Liess, Furong Huang

ICMLW 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

ICMLW 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

NeurIPSW 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

ICLR 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

ICLR 2024 PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts Bang An, Sicheng Zhu, Michael-Andrei Panaitescu-Liess, Chaithanya Kumar Mummadi, Furong Huang

NeurIPSW 2024 PoisonedParrot: Subtle Data Poisoning Attacks to Elicit Copyright-Infringing Content from Large Language Models Michael-Andrei Panaitescu-Liess, Pankayaraj Pathmanathan, Yigitcan Kaya, Zora Che, Bang An, Sicheng Zhu, Aakriti Agrawal, Furong Huang

ICMLW 2023 Like Oil and Water: Group Robustness and Poisoning Defenses Don’t Mix Michael-Andrei Panaitescu-Liess, Yigitcan Kaya, Tudor Dumitras

ICMLW 2023 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, Furong Huang

NeurIPS 2021 Qu-ANTI-Zation: Exploiting Quantization Artifacts for Achieving Adversarial Outcomes Sanghyun Hong, Michael-Andrei Panaitescu-Liess, Yigitcan Kaya, Tudor Dumitras