Beyond Visual Safety: Jailbreaking Multimodal Large Language Models for Harmful Image Generation via Semantic-Agnostic Inputs

Documenti analoghi

• Universally Unfiltered and Unseen:Input-Agnostic Multimodal Jailbreaks against Text-to-Image Model Safeguards
  di: Yan, Song, et al.
  Pubblicazione: (2025)
• VRSA: Jailbreaking Multimodal Large Language Models through Visual Reasoning Sequential Attack
  di: Zhao, Shiji, et al.
  Pubblicazione: (2025)
• Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models
  di: Li, Yifan, et al.
  Pubblicazione: (2024)
• GAMBIT: A Gamified Jailbreak Framework for Multimodal Large Language Models
  di: Hu, Xiangdong, et al.
  Pubblicazione: (2026)
• SDEval: Safety Dynamic Evaluation for Multimodal Large Language Models
  di: Wang, Hanqing, et al.
  Pubblicazione: (2025)