9 papers
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…
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…
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…
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…
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…
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…