Zhun Wang

发表论文 32 篇 · 总被引 479 次 · h-index 12

代表论文

• PromptArmor: Simple yet Effective Prompt Injection Defenses (2025 · arXiv.org · 被引 121)
• Progent: Securing AI Agents with Privilege Control (2025 · 被引 111)
• CyberGym: Evaluating AI Agents'Real-World Cybersecurity Capabilities at Scale (2025 · 被引 66)
• AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents (2025 · 被引 46)
• Frontier AI's Impact on the Cybersecurity Landscape (2025 · arXiv.org · 被引 35)
• AGENTVIGIL: Automatic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents (2025 · Conference on Empirical Methods in Natural Language Processing · 被引 34)