… It was developed as a collaboration between UC Berkeley, the Max Planck Institute for Security and Privacy, UC Santa Barbara, and Arizona State University with contributions from security researchers at Anthropic, OpenAI, and Google , as a follow-on to the CyberGym vulnerability-reproduction benchm… …
… But looking at the rate of progress, it is unlikely that the gap between frontier models’ vulnerability discovery and exploitation abilities will last very long. …
… Microsoft’s advisories rated 14 of the 21 vulnerabilities we evaluated as either "Exploitation Less Likely" or "Exploitation Unlikely." Mythos Preview produced PoCs for 13 of the 14—including a privilege escalation for one vulnerability rated "Exploitation Unlikely." Microsoft's rating system is cu… …
… We’ve also begun our Cyber Verification Program , which allows security professionals using our models for legitimate cybersecurity purposes such as vulnerability research, penetration testing, and red-teaming to do so without certain safeguards designed to prevent cyber misuse. …
… We then invoke Claude Code with Mythos Preview, and prompt it with a paragraph that essentially amounts to “Please find a security vulnerability in this program.” We then let Claude run and agentically experiment. …
… We provide evidence-based analysis about AI’s implications for cybersecurity, national security, and autonomous systems. …
… However, bug bounties reflect only the defensive value of a vulnerability to an organization, not the offensive value that could be realized through exploitation in the wild. …
… High-risk dual use actions include: Hacking, penetration testing, red teaming, and bug bounties; Gaining cyber access through unexpected or unauthorized means: exploitation, credential attacks brute force, spraying, stuffing, theft , and authentication bypasses; Privilege escalation, lateral moveme… …
… Vulnerability primer Now that we understand how Wasm modules and bind works, let’s review the discovered vulnerability’s root cause. …
… Because of the urgency of this moment in the evolution of AI and cybersecurity, we dedicated researchers to making Claude better at key skills like code vulnerability discovery and patching. …