Claude Mythos Executes End-to-End Intrusion From Initial Access to Full Domain Compromise
Anthropic's Claude Mythos Preview, its most cyber-capable model, autonomously completed an end-to-end enterprise intrusion simulation in restricted-access testing.
Anthropic's April 2026 system card describes Claude Mythos Preview as the first model to solve a private cyber range end to end and finish a corporate-network attack simulation an expert would need 10+ hours to complete. It scored 100% pass@1 on a 35-challenge Cybench subset and 0.83 on CyberGym versus 0.67 for Claude Opus 4.6. The model is limited to vetted partners under Project Glasswing; it failed an OT cyber range and could not find novel exploits in a fully patched sandbox.
Learning Intrusion Response Strategies for OT Systems
Researchers model OT intrusion response as a POMDP and train PPO-based automated response strategies effective against MITRE attacks in an emulated OT system.
The paper formalizes automated intrusion response for OT systems as a partially observable Markov decision process, with partial observability modeled from traffic measurements. Learning-based solution methods built on PPO are developed and evaluated on an emulated OT system. The resulting response strategies proved effective against several types of MITRE attacks for the studied use case.