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
ACM FAccT · Event date June 25, 2026 - June 28, 2026

ACM FAccT 2026

event past event AI ComplianceModel EvaluationAI Red Teaming
Why it matters
June 25, 2026 - June 28, 2026
Event archive

ACM FAccT 2026 convened interdisciplinary research on responsible, safe, ethical, and trustworthy computing in Montréal. Its program covered AI audits and evaluation practice, red teaming and adversarial testing, assurance and deployment policy, regulation and governance, sociotechnical safety, threat models, transparency, and value alignment.

My takeaway: The archive is useful for testing whether a security evaluation measures the right harms and affected groups. Pair technical attack success with institutional accountability, deployment context, recourse, transparency, and distributional impact; distinguish empirical audits from normative or legal analysis.
Keep exploring

More curated notes connected through AI Compliance 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.