4 papers
Beyond Appearance Shifts: Task-Semantic Action Calibration for VLA Models
Shuaijun Liu, Feiyang You, Chengyu Wu +6
Vision-language-action (VLA) models have achieved strong performance in embodied manipulation, but still struggle to distinguish between changes that should preserve behavior and t…
Making Every Step Effective: Jailbreaking Large Vision-Language Models Through Hierarchical KV Equalization
Shuyang Hao, Yiwei Wang, Bryan Hooi +4
In the realm of large vision-language models (LVLMs), adversarial jailbreak attacks serve as a red-teaming approach to identify safety vulnerabilities of these models and their ass…
Tit-for-Tat: Safeguarding Large Vision-Language Models Against Jailbreak Attacks via Adversarial Defense
Shuyang Hao, Yiwei Wang, Bryan Hooi +5
Deploying large vision-language models (LVLMs) introduces a unique vulnerability: susceptibility to malicious attacks via visual inputs. However, existing defense methods suffer fr…
Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models
Shuyang Hao, Bryan Hooi, Jun Liu +3
Despite inheriting security measures from underlying language models, Vision-Language Models (VLMs) may still be vulnerable to safety alignment issues. Through empirical analysis,…