← authors · overview

• Robust Physical-World Attacks on Deep Learning Models
  2017 · 508 citations
• TrustLLM: Trustworthiness in Large Language Models
  2024 · 53 citations
• Deceptprompt: Exploiting Llm-driven Code Generation Via Adversarial Natural Language Instructions
  2023 · 46 citations
• MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machines
  2025 · 12 citations
• Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses
  2026
• Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses
  2026
• AgentDyn: Are Your Agent Security Defenses Deployable in Real-World Dynamic Environments?
  2026
• dVLM-AD: Enhance Diffusion Vision-Language-Model for Driving via Controllable Reasoning
  2025
• PRISM: Robust VLM Alignment with Principled Reasoning for Integrated Safety in Multimodality
  2025
• ARMOR: Aligning Secure and Safe Large Language Models via Meticulous Reasoning
  2025
• Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Driving
  2019