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 AISec · Event date November 15, 2026

ACM AISec 2026

event upcoming Adversarial MLAI Red TeamingAgent Security
Why it matters
November 15, 2026
Scheduled event

The 19th ACM Workshop on Artificial Intelligence and Security is listed for November 15 in ACM CCS registration, alongside related workshops in The Hague. It covers adversarial ML, model privacy, AI misuse, foundation-model red teaming, dangerous-capability evaluation, deceptive alignment, multi-agent risk, and autonomous-agent containment.

My takeaway: AISec is a high-value research pipeline because accepted work must state its threat model and is published archivally. Review its program alongside the adjacent agent-security, large-model privacy and safety, and deepfake-security workshops; prioritize papers with released artifacts and adaptive attackers.
Keep exploring

More curated notes connected through Adversarial ML 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.