{
  "id": 12259,
  "url": "https://arxiv.org/abs/2607.17779v1",
  "title": "Dynamic Defense Profiling Enables Cognitive Jailbreak of Text-to-Image Models",
  "summary": "Text-to-Image (T2I) generative models have achieved remarkable progress in synthesizing high-quality visual content, yet they remain vulnerable to adversarial misuse, particularly in generating Not-Safe-For-Work (NSFW) images. Most existing jailbreak attacks primarily rely on heuristic prompt engineering or black-box optimization, treating model feedback as a binary signal (success or failure). This coarse-grained paradigm overlooks the rich information embedded in diverse failure modes, such as",
  "authors": "Dongdong Yang, Deyue Zhang, Zhao Liu, Zonghao Ying, Wenzhuo Xu, Jiankai Jin, Xiangzheng Zhang, Quanchen Zou",
  "category": "research",
  "topics": "safety-alignment,military-security",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-20T10:09:30.000Z",
  "fetched_at": "2026-07-21T05:10:12.656Z",
  "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/12259",
  "original_url": "https://arxiv.org/abs/2607.17779v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}