The Hacker News AI Security · November 11, 2026

Lazarus model backdoors: verify weight provenance and contain agent actions

Why it matters

Microsoft’s Lazarus research shows how modifying a few dormant model neurons can create triggered command output while leaving ordinary evaluations largely intact. The attacker needs write access to a checkpoint; this is a model-integrity threat rather than an input-only prompt attack. Microsoft reports no observed threat-actor use of the technique. Weight inspection can provide evidence of tampering, but a passing scan cannot establish safety.

My takeaway: Record publisher, base model and hashes for every checkpoint. Compare unexpected weight changes against the declared base and retain audit results through updates. Combine behavioral tests with restricted tool permissions, isolated execution and controlled egress. Plan for a compromised model instead of making a scan or a clean benchmark score the sole deployment gate.
Keep exploring

More curated notes connected through Adversarial ML and Agent Security.

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.