Jingzhi Jiang

The paper introduces Trident, a novel malware detection system that combines static features, LLM-derived behavioral rules, and direct LLM analysis to achieve superior robustness against concept drift compared to traditional methods.

The paper introduces CyberGym-E2E, a large-scale, end-to-end benchmark designed to comprehensively evaluate AI agents' capabilities across the entire lifecycle of real-world software vulnerability discovery, proof-of-concept generation, and patch creation.