{
  "id": 4643,
  "url": "https://arxiv.org/abs/2605.09225v1",
  "title": "The Art of the Jailbreak: Formulating Jailbreak Attacks for LLM Security Beyond Binary Scoring",
  "summary": "Jailbreak attacks -- adversarial prompts that bypass LLM alignment through purely linguistic manipulation -- pose a growing operational security threat, yet the field lacks large-scale, reproducible infrastructure for generating, categorizing, and evaluating them systematically. This paper addresses that gap with three contributions. (1) Large-scale compositional jailbreak dataset. We construct 114,000 adversarial prompts by applying 912 composing strategies to 125 harmful seed prompts from Jail",
  "authors": "Ismail Hossain, Tanzim Ahad, Md Jahangir Alam, Sai Puppala, Syed Bahauddin Alam, Sajedul Talukder",
  "category": "research",
  "topics": "safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-09T23:51:18.000Z",
  "fetched_at": "2026-07-14T16:31:08.357Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4643",
  "original_url": "https://arxiv.org/abs/2605.09225v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}