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
garak Releases · October 16, 2026

garak 0.17.1: distinguish repeated-attempt success from unscored tests

tool AI Red TeamingModel Evaluation
Why it matters

garak 0.17.1 adds hit@k, estimating whether at least one of k sampled tries succeeds, averaged across eligible prompts. Prompts with fewer than k scoreable outputs are excluded and their coverage must be tracked. It also fixes FileDetector so an unexamined file is not counted as a pass. These changes affect how results are interpreted; a score change after upgrading need not mean the target model changed.

My takeaway: Pin the scanner, model, prompts, and generation settings before comparing runs. Report k, eligible prompt counts, and unscored outputs alongside scores. Use benign fixtures with a known mixed pass/fail pattern and an unexamined file to check aggregation and missing-result handling. Review historical results affected by detector fixes rather than treating them as a stable baseline.
Keep exploring

More curated notes connected through AI Red Teaming and Model Evaluation.

OpenAI News · framework

Pacing model development in an era of cyber-critical capabilities

OpenAI says preliminary evidence that Astra may meet its Critical cybersecurity threshold led it to pause frontier reinforcement-learning work for two weeks and keep its largest planned run on hold. New safeguards include stronger workload and network isolation, continuous boundary testing, token-level monitoring that escalates suspicious tool activity, and broader alignment checks for deception, reward hacking, and unauthorized access.

OWASP GenAI Security Project · guide

OWASP Top 10 for Agentic Applications for 2026

OWASP's community guide organizes agentic-system risk into ten categories, including goal hijacking, tool misuse, identity and privilege abuse, memory poisoning, insecure inter-agent communication, cascading failures, and rogue-agent behavior. It provides a shared taxonomy and mitigation starting point rather than a certification checklist or evidence that a deployed system is secure.

OpenAI News · framework

A blueprint for democratic governance of frontier AI

OpenAI proposes a three-part U.S. frontier-AI governance model: harmonize emerging state safety laws into a federal baseline, strengthen CAISI as an evaluation and standards institution, and coordinate a broader resilience program. Proposed controls include severe-risk evaluations, transparency reports, independent audits, safety-incident reporting, model-weight security, whistleblower protection, and periodic technical assessments.