{
  "id": 3143,
  "url": "https://arxiv.org/abs/2607.02961v1",
  "title": "Overloading Large Vision-Language Models for Jailbreaking",
  "summary": "Large Vision-Language Models (LVLMs) exhibit remarkable vision-language capabilities and are increasingly deployed in real-world applications such as personal assistants, document analysis systems, and embodied agents. However, their dual-modal attack surfaces make them vulnerable to jailbreak attacks. Existing LVLM jailbreaks rely on simple designs, e.g., short text and out-of-distribution images. Nevertheless, recent advancements in both large language model backbones and multimodal mechanisms",
  "authors": "Haoyu Zhang, Yangyang Guo, Mohan Kankanhalli",
  "category": "research",
  "topics": "safety-alignment,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-03T05:09:03.000Z",
  "fetched_at": "2026-07-14T16:11:46.979Z",
  "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/3143",
  "original_url": "https://arxiv.org/abs/2607.02961v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}