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 Security & Privacy · Event date May 18, 2026 - May 21, 2026

IEEE Symposium on Security and Privacy 2026

event past event Adversarial MLAI Red TeamingAgent Security
Why it matters
May 18, 2026 - May 21, 2026
Event archive

The 47th IEEE Symposium on Security and Privacy and its workshops convened in San Francisco with a dedicated machine-learning security track and research on LLM privacy, alignment, jailbreaks, attacks, and defenses. The co-located Secure Agents for Generative AI workshop concentrated specifically on agent architectures and their security boundaries.

My takeaway: Use the proceedings to extract explicit attacker capabilities, system assumptions, datasets, and artifacts. Favor results evaluated against adaptive attacks and realistic tool or data access, and convert relevant papers into product-level tests rather than assuming model-only defenses secure an agent workflow.
Keep exploring

More curated notes connected through Adversarial ML and AI Red Teaming.

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.

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.

OECD.AI Wonk · guide

A five-step roadmap to closing the AI evaluation gap

The roadmap addresses evaluation results that overstate real-world performance or fail to transfer across deployment contexts. Its five steps balance standardized and local tests, evaluate throughout the lifecycle, build qualified assurance and communication capacity, tailor tests to each value-chain actor and technology, and use a coordinated, trusted process for updating methods.