Research
Here you will find my research contributions in the field of cybersecurity.
ARTEMIS Comparing AI Agents to Cybersecurity Professionals in Real-World Penetration Testing. Featured in the Wall Street Journal. Cybench A Benchmark for Evaluating the Cybersecurity Capabilities and Risks of Language Models. HotelDruid Authenticated RCE CVE-2023-34854: Authenticated remote code execution via backup/restore functionality.