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
IEEE SaTML · Event date March 23, 2026 - March 25, 2026

IEEE SaTML 2026

event past event Adversarial MLModel EvaluationAI Red Teaming
Why it matters
March 23, 2026 - March 25, 2026
Event archive

IEEE SaTML 2026 brought secure and trustworthy machine-learning research to the Technical University of Munich. The program addressed attacks and defenses, system and algorithm verification, ML privacy and forensics, interpretability and fairness, trustworthy data curation, and practical evaluation of learning systems.

My takeaway: SaTML is most valuable when papers make trust claims falsifiable. Record the threat model, security property, evaluation distribution, adaptive attacker, proof or empirical evidence, and artifact availability; avoid translating narrow benchmark robustness into broad claims about deployed-system safety.
Keep exploring

More curated notes connected through Adversarial ML 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.

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.

OpenAI News · framework

OpenAI’s Frontier Governance Framework

OpenAI's 22-page Frontier Governance Framework maps its frontier-model processes to California's Transparency in Frontier AI Act and the EU AI Act's general-purpose AI code. It documents lifecycle risk assessment, cyber-offense and other risk tiers, mitigation and residual-risk decisions, critical-incident handling, security risk management, model reporting, external review, responsibility allocation, and change control.