11 papers
ReasonBreak: Probing Vulnerabilities in Reasoning-Enabled Vision-Language-Action Models for Autonomous Driving
Mohammadreza Teymoorianfard, Jean-Philippe Monteuuis, Jonathan Petit +1
Vision-Language-Action (VLA) models with integrated reasoning have been proposed for end-to-end autonomous driving, assuming a tight coupling between reasoning and trajectory gener…
Forget to Know, Remember to Use: Context-Aware Unlearning for Large Language Models
Yuefeng Peng, Parnian Afshar, Megan Ganji +4
Large language models may encode sensitive information or outdated knowledge that needs to be removed, to ensure responsible and compliant model responses. Unlearning has emerged a…
Codec-Robust Attacks on Audio LLMs
Jaechul Roh, Jean-Philippe Monteuuis, Jonathan Petit +1
Prior attacks on Audio Large Language Models (Audio LLMs) demonstrated that carefully crafted waveform-domain perturbations can force targeted adversarial outputs. As a defense mec…
Membership Inference Attacks on Vision-Language-Action Models
Yuefeng Peng, Mingzhe Li, Kejing Xia +2
Membership inference attacks (MIAs) have been extensively studied in large language models (LLMs) and vision-language models (VLMs), yet their implications for vision-language-acti…
Benign Fine-Tuning Breaks Safety Alignment in Audio LLMs
Jaechul Roh, Amir Houmansadr
Prior work shows that fine-tuning aligned models on benign data degrades safety in text and vision modalities, and that proximity to harmful content in representation space predict…
Bob's Confetti: Phonetic Memorization Attacks in Music and Video Generation
Jaechul Roh, Zachary Novack, Yuefeng Peng +3
Generative AI systems for music and video commonly use text-based filters to prevent regurgitation of copyrighted material. We expose a significant vulnerability in this approach b…