VisualLeakBench: Auditing the Fragility of Large Vision-Language Models against PII Leakage and Social Engineering

As Large Vision-Language Models LVLMs are increasingly deployed in agent-integrated workflows and other deployment-relevant settings, their robustness against semantic visual attacks remains under-evaluated -- alignment is typically tested on explicit harmful content rather than privacy-critical...

STAC: When Innocent Tools Form Dangerous Chains to Jailbreak LLM Agents

As LLMs advance into autonomous agents with tool-use capabilities, they introduce security challenges that extend beyond traditional content-based LLM safety concerns. This paper introduces Sequential Tool Attack Chaining STAC, a novel multi-turn attack framework that exploits agent tool use. STA...