{
  "id": 16171,
  "url": "https://arxiv.org/abs/2608.00973v1",
  "title": "Mind the Gap: Zero-Query Jailbreaks via Filter-Generator Discrepancy in Text-to-Image Systems",
  "summary": "Text-to-image (T2I) systems typically have prompt-level safety filters before the generator to block unsafe requests, yet such systems remain vulnerable to malicious jailbreak prompts. Transfer-based attacks construct adversarial prompts offline without querying the target, but they tend to overfit to a single surrogate. Moreover, they explore a large search space in which semantic or perceptual similarity alone cannot guarantee both filter evasion and preservation of the unsafe generation inten",
  "authors": "Wanguang Li, Zhaoxin Wang, Handing Wang",
  "category": "research",
  "topics": "safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-02T03:53:30.000Z",
  "fetched_at": "2026-08-04T05:10:21.797Z",
  "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/16171",
  "original_url": "https://arxiv.org/abs/2608.00973v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}