N. Gong

发表论文 230 篇 · 总被引 15384 次 · h-index 64

代表论文

• WAInjectBench: Benchmarking Prompt Injection Detections for Web Agents (2025 · arXiv.org · 被引 21)
• MalTool: Malicious Tool Attacks on LLM Agents (2026 · arXiv.org · 被引 20)
• Provably Robust Federated Reinforcement Learning (2025 · The Web Conference · 被引 18)
• A Framework for Formalizing LLM Agent Security (2026 · arXiv.org · 被引 17)
• WebSentinel: Detecting and Localizing Prompt Injection Attacks for Web Agents (2026 · arXiv.org · 被引 10)
• A Systematic Survey of Model Extraction Attacks and Defenses: State-of-the-Art and Perspectives (2025 · arXiv.org · 被引 10)