Jiawei Zhang

Any-Depth Alignment: Unlocking Innate Safety Alignment of LLMs to Any-Depth

ARMs: Adaptive Red-Teaming Agent against Multimodal Models with Plug-and-Play Attacks

GraphQ-LM: Scalable Graph Representation for Large Language Models via Residual Vector Quantization

MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models

EIA: ENVIRONMENTAL INJECTION ATTACK ON GENERALIST WEB AGENTS FOR PRIVACY LEAKAGE

AdvAgent: Controllable Blackbox Red-teaming on Web Agents

SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation Models

GuardAgent: Safeguard LLM Agents via Knowledge-Enabled Reasoning

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

KnowHalu: Multi-Form Knowledge Enhanced Hallucination Detection

UDora: A Unified Red Teaming Framework against LLM Agents by Dynamically Hijacking Their Own Reasoning

AdvWeb: Controllable Black-box Attacks on VLM-powered Web Agents

SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation Models