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
The Hacker News AI Security · November 3, 2026

LLMjacking detection: watch credential probes and unauthorized model enablement

news Agent SecurityAI EngineeringAI Red Teaming
Why it matters

Mandiant’s 2026 investigations trace stolen cloud credentials through privilege changes, model-service enablement and resale of inference access. Some actors validated keys with single-token requests before scaling abuse. The report supplies cloud audit events and logging prerequisites for hunting these stages; billing spikes can arrive after access and persistence are established.

My takeaway: Verify that inference logs are enabled and actually capture an authorized test request. Correlate unusual low-volume probes with new keys, service enablement and logging changes; legitimate health checks can look similar. Restrict who can enable models or mint credentials, enforce available usage limits, and investigate persistence as well as revoking exposed keys. Treat budget alerts as notifications, not guaranteed spending stops.
Keep exploring

More curated notes connected through Agent Security and AI Engineering.

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.