Red-teaming the Multimodal Reasoning: Jailbreaking Vision-Language Models via Cross-modal Entanglement Attacks

Ähnliche Einträge

• from Benign import Toxic: Jailbreaking the Language Model via Adversarial Metaphors
  von: Yan, Yu, et al.
  Veröffentlicht: (2025)
• PolyJailbreak: Cross-Modal Jailbreaking Attacks on Black-Box Multimodal LLMs
  von: Wang, Xinkai, et al.
  Veröffentlicht: (2025)
• STARE: Step-wise Temporal Alignment and Red-teaming Engine for Multi-modal Toxicity Attack
  von: Mao, Xutao, et al.
  Veröffentlicht: (2026)
• Towards Robust Multimodal Large Language Models Against Jailbreak Attacks
  von: Yin, Ziyi, et al.
  Veröffentlicht: (2025)
• A Cross-Language Investigation into Jailbreak Attacks in Large Language Models
  von: Li, Jie, et al.
  Veröffentlicht: (2024)