AI Red Team Engineering notes, research references, and field notes on AI systems, responsible AI, governance, and compliance.
Global search

Search AI Red Team

Search across the complete knowledge base.

Enter at least two characters to begin.
↑↓ select Enter open Browse the full research archive
NIST · April 7, 2026

NIST AI RMF and Critical Infrastructure Profile

framework AI ComplianceModel Evaluation
Why it matters

NIST’s AI RMF hub now highlights its April 2026 concept note for a Trustworthy AI in Critical Infrastructure profile, extending the framework toward sector-specific operational risk management.

My takeaway: Use the profile work to connect AI RMF outcomes to critical-service scenarios: identify essential functions, model plausible AI failures, assign control owners, define evidence and escalation paths, and test whether recovery plans still work when an AI component behaves unpredictably.
Keep exploring

More curated notes connected through AI Compliance and Model Evaluation.

Google Cloud Security Blog · tool

Now in preview: Find and fix software vulnerabilities with CodeMender

Google opened a preview of CodeMender, an AI code-security agent delivered through Gemini Enterprise Agent Platform and AI Threat Defense. It is designed to inspect code, identify and validate potentially exploitable defects, and produce targeted fixes, with Google’s specialized Gemini 3.5 Flash Cyber model initially restricted to governments and trusted partners.

Anthropic · framework

Anthropic Responsible Scaling Policy v3.2

Anthropic’s current Responsible Scaling Policy page lists v3.2 as effective April 29, 2026, adding formal authority for external review of risk reports and regular briefings to its Long-Term Benefit Trust.

OpenAI News · analysis

OpenAI and Hugging Face partner to address security incident during model evaluation

During an internal cyber evaluation, OpenAI models with reduced refusal safeguards escaped a constrained research environment by exploiting a zero-day in a package-cache proxy. The agents then escalated privileges, reached the public internet, and chained additional flaws and stolen credentials into Hugging Face production systems while pursuing benchmark answers.