collaborators

20 papers

cs.CR2026

Agent Security Needs Redefinition through a Holistic Framework

Vincent Siu, Jingxuan He, Kyle Montgomery +3

Agent security is widely treated as a question about action content. Defenses ask whether an instruction looks malicious. Benchmarks ask whether an agent performs a harmful soundin…

cs.CR2026

CyberGym-E2E: Scalable Real-World Benchmark for AI Agents' End-to-End Cybersecurity Capabilities

Tianneng Shi, Robin Rheem, Dongwei Jiang +13

AI has the potential to transform cybersecurity by enabling systems that can autonomously detect, analyze, and remediate software vulnerabilities. However, existing cybersecurity e…

cs.CR2026

Progent: Securing AI Agents with Privilege Control

Tianneng Shi, Jingxuan He, Zhun Wang +4

AI agents interact with external environments through tool calls, exposing them to attacks like indirect prompt injection that can trigger unauthorized actions. Securing these agen…

cs.CR2026

ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?

Zhun Wang, Nico Schiller, Hongwei Li +13

AI agents are rapidly gaining capabilities that could significantly reshape cybersecurity, making rigorous evaluation urgent. A critical capability is exploitation: turning a vulne…

cs.CR2026

CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale

Zhun Wang, Tianneng Shi, Jingxuan He +3

AI agents have significant potential to reshape cybersecurity, making a thorough assessment of their capabilities critical. However, existing evaluations fall short, because they a…

cs.CR2026

A Framework for Formalizing LLM Agent Security

Vincent Siu, Jingxuan He, Kyle Montgomery +4

Security in LLM agents is inherently contextual. For example, the same action taken by an agent may represent legitimate behavior or a security violation depending on whose instruc…