ImgTrojan: Jailbreaking Vision-Language Models with ONE Image

Documenti analoghi

• TAIJI: Textual Anchoring for Immunizing Jailbreak Images in Vision Language Models
  di: Yin, Xiangyu, et al.
  Pubblicazione: (2025)
• Img-Diff: Contrastive Data Synthesis for Multimodal Large Language Models
  di: Jiao, Qirui, et al.
  Pubblicazione: (2024)
• Learning to Detect Unknown Jailbreak Attacks in Large Vision-Language Models
  di: Liang, Shuang, et al.
  Pubblicazione: (2025)
• TEMPLE: Incentivizing Temporal Understanding of Video Large Language Models via Progressive Pre-SFT Alignment
  di: Li, Shicheng, et al.
  Pubblicazione: (2025)
• Mind the Trojan Horse: Image Prompt Adapter Enabling Scalable and Deceptive Jailbreaking
  di: Chen, Junxi, et al.
  Pubblicazione: (2025)