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
Internet Society / NDSS · Event date February 23, 2026 - February 27, 2026

NDSS Symposium 2026

event past event AI Red TeamingAdversarial MLAgent Security
Why it matters
February 23, 2026 - February 27, 2026
Event archive

NDSS 2026 combined systems-security research with dedicated AI-security sessions and the co-located LAST-X workshop on LLM-assisted security and trust exploration. The archived program includes attacks on LLM availability and alignment, watermark robustness, AI-enabled phishing defenses, adversarial ML, and evaluations of LLMs used in security work.

My takeaway: The archive offers papers, slides, and videos that can seed adversarial test cases. Separate attacks on models from attacks on complete applications, verify whether demonstrations survive realistic constraints, and track how LLM-assisted defensive tools are evaluated for false confidence, poisoning, and operator misuse.
Keep exploring

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

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.