{
  "id": 16569,
  "url": "https://arxiv.org/abs/2608.03070v1",
  "title": "AI Security Leaderboard: Methodology, Results and Minimal Standard",
  "summary": "Frontier AI model developers increasingly rely on layered safeguards to prevent catastrophic misuse, but little public evidence exists on how much protection these safeguards provide, or how consistently across developers. We introduce the FAR.AI Minimal Standard for Safeguards, Version 1.0: a taxonomy of 67 readily accessible static jailbreak techniques, a method for composing them into a very large attack space, and a benchmark of flagship models against a sample of it. We evaluate Claude Fabl",
  "authors": "Jasper Timm, Lukas Struppek, Ziwei Xu, Grace Cheong, Oscar Mata, Dan Zhao, Mick Yang, Isadora De Andrade, Xiaojun Jia, Yiming Li, Samuel Bauer, Heather McIntyre, Adam Gleave, Edward Yee, Kellin Pelrine",
  "category": "research",
  "topics": "safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-04T03:32:19.000Z",
  "fetched_at": "2026-08-05T05:10:44.550Z",
  "source_slug": "x-arxiv-red-teaming-query",
  "source_name": "arXiv red teaming query",
  "source_homepage": "https://arxiv.org/a/redteam",
  "ethics_ai_record_url": "https://ethics.ai/record/16569",
  "original_url": "https://arxiv.org/abs/2608.03070v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}