{
  "id": 14849,
  "url": "https://arxiv.org/abs/2607.26574v1",
  "title": "Recover, Decode, Reguard: Guard-Agnostic Defense Amplification againstEncoded VLM Jailbreaks",
  "summary": "Safety classifiers (\"guards\") are the dominant black-box defense for vision-language models, yet they judge an input's surface form, not its meaning: a harmful request re-encoded as set theory, formal logic, a rare language, code, or an image of text slips past a guard that would block it in plain language -- the decode gap. The natural fix is a guard-agnostic recover-and-decode amplifier that transcribes image content and restates encoded text into its plain payload before the guard, so any off",
  "authors": "Haoyu Zhang, Zhuoxi Wang, Shibo Zheng, Zijian Xiao, Xiangchen Guan, Mohammad Zandsalimy, Shanu Sushmita",
  "category": "research",
  "topics": "safety-alignment,military-security",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-29T07:53:35.000Z",
  "fetched_at": "2026-07-30T05:10:24.387Z",
  "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/14849",
  "original_url": "https://arxiv.org/abs/2607.26574v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}