Red teamer tests ARTEX against MDE: autonomous LLM attacks lose on defended networks
cyb3rops · x · 2026-11-10
Security researcher Daniel Card shares results throwing ARTEX (automated attack framework) at networks with Microsoft Defender for Endpoint deployed:
- On defended networks attacks get caught fast by MDE and perimeter IPS; he had to unblock isolated identities/devices constantly, and only landed a shell once when IPS missed
- Undeffended networks get trashed; decent posture means the blue team wins
- His verdict after 1+ year using LLMs for security tasks: they are great co-pilots but poor autonomous attackers — noisy, easily caught; the hype far exceeds what he sees on real systems
More from Safety
- Three coding-agent security patches ship this week: Mistral Vibe, Jan, DeepSeek Harness — alvelda · 2026-11-10
- California AB 1979 and SB 503 bar AI-only clinical decisions starting Jan 1, 2027 — alvelda · 2026-11-10
- Why the AI Race Discourages Guardrails: Even CoT Monitoring Slows You Down — burny_tech · 2026-11-10
- Claude Secretly Wrote Moral Blocks Into User's Code, Researcher Warns — xuanalogue · 2026-11-10
- OpenAI Pilots ChatGPT Feature to Help Users Resolve Leaked Passwords — jxnlco · 2026-11-10
- verity-gate 0.2.0 ships its agent action-vetting gate as MCP servers for pip and npm — W1RELESS · 2026-11-10