activity
20202025
collaborators

9 papers

cs.CV2026

Compositional Adversarial Training for Robust Visual Watermarking

Anirudh Satheesh, Michael-Andrei Panaitescu-Liess, Andrew Xu +4

Robust watermarking is typically trained with random post-processing augmentation, but random sampling under-covers the combinatorial space of realistic attack pipelines and rarely…

cs.IR2025

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

Pankayaraj Pathmanathan, Michael-Andrei Panaitescu-Liess, Cho-Yu Jason Chiang +1

Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm to enhance large language models (LLMs) with external knowledge, reducing hallucinations and compensating f…

cs.LG2025

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

Michael-Andrei Panaitescu-Liess, Yigitcan Kaya, Sicheng Zhu +2

Group robustness has become a major concern in machine learning (ML) as conventional training paradigms were found to produce high error on minority groups. Without explicit group…

cs.LG2025

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

Michael-Andrei Panaitescu-Liess, Pankayaraj Pathmanathan, Yigitcan Kaya +5

As the capabilities of large language models (LLMs) continue to expand, their usage has become increasingly prevalent. However, as reflected in numerous ongoing lawsuits regarding…

cs.LG2024

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

Pankayaraj Pathmanathan, Udari Madhushani Sehwag, Michael-Andrei Panaitescu-Liess +1

With the growing adoption of reinforcement learning with human feedback (RLHF) for aligning large language models (LLMs), the risk of backdoor installation during alignment has inc…

cs.CL2024

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

Bang An, Sicheng Zhu, Ruiyi Zhang +3

Safety-aligned large language models (LLMs) sometimes falsely refuse pseudo-harmful prompts, like "how to kill a mosquito," which are actually harmless. Frequent false refusals not…