Black Hat · August 29, 2026

Black Hat Asia 2026 | Large-Scale macOS PID-Domain Vulnerability Discovery with LLM Reasoning

video AI Red Teaming Model Evaluation AI Engineering

Black Hat Asia 2026 | Large-Scale macOS PID-Domain Vulnerability Discovery with LLM Reasoning video thumbnail

Why it matters

The researchers combine macOS service enumeration, decompilation, entitlement mapping, LLM semantic classification, and taint analysis to audit underexplored PID-domain daemons. Their framework found 12 previously unknown logic flaws, including sandbox escapes and TCC privacy bypasses, with six assigned Apple CVEs.

My takeaway: Use the LLM to prioritize sensitive operations, then require deterministic entitlement and data-flow evidence before accepting a finding. Re-run the pipeline against patched builds, preserve prompts and decompiler output for review, and isolate automated exploit validation from developer credentials and production networks.

Keep exploring

More curated notes connected through AI Red Teaming and Model Evaluation.

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.