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
ACSAC / AIDC · Event date December 7, 2026

ACSAC AIDC 2026: Agentic AI in Cyber Operations

event upcoming Agent SecurityAI Red TeamingModel Evaluation
Why it matters
December 7, 2026
Scheduled event

AIDC is a December 7 ACSAC workshop in Los Angeles on agentic AI for offensive and defensive cyber operations. Its research scope includes interactions between attacking and defending agents, deception, input manipulation, poisoning, and failures in operational environments. The emphasis is on evaluating complete cyber workflows rather than isolated model capabilities.

My takeaway: Look for experiments that state the environment, attacker access, success criteria, and limits on agent actions. Compare defensive gains with failure modes, human intervention, and the cost of operating the system.
Keep exploring

More curated notes connected through Agent Security and AI Red Teaming.

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.