AI to defend critical infrastructure
Jan 8, 2026

Summary
This post details a partnership with PNNL to explore AI for critical infrastructure cybersecurity defense. It describes using Claude to emulate cyber attacks on a simulated water treatment plant, significantly accelerating adversary emulation from weeks to hours. A key technical detail is Claude's resourcefulness in bypassing a Windows User Account Control (UAC) security feature when a pre-defined tool failed, demonstrating emergent problem-solving capabilities in a cybersecurity context. The work involved developing a 'scaffold' for Claude to translate natural language prompts into attack chains using pre-defined code-based tools.
More from the AI-Resistant Technical Evaluation Design trail
- An alignment assessment of recent cybersecurity incidents
- Discovering cryptographic weaknesses with Claude
- Evaluating Claude’s bioinformatics research capabilities with BioMysteryBench
- A “diff” tool for AI: Finding behavioral differences in new models
- Eval awareness in Claude Opus 4.6’s BrowseComp performance