Zhen Xiang

Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models

Computer-Use Agent Frameworks Can Expose Realistic Risks Through Tactics, Techniques, and Procedures

SoSBench: Benchmarking Safety Alignment on Six Scientific Domains

Position: Multi-Faceted Studies on Data Poisoning can Advance LLM Development

SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents

Memory Injection Attacks on LLM Agents via Query-Only Interaction

MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models

Physical Backdoor Attack can Jeopardize Driving with Vision-Large-Language Models

GuardAgent: Safeguard LLM Agents via Knowledge-Enabled Reasoning

GuardAgent: Safeguard LLM Agent by a Guard Agent via Knowledge-Enabled Reasoning

IDS-Agent: An LLM Agent for Explainable Intrusion Detection in IoT Networks