Arondight: Red Teaming Large Vision Language Models with Auto-generated Multi-modal Jailbreak Prompts

Ähnliche Einträge

• Beyond Text: Multimodal Jailbreaking of Vision-Language and Audio Models through Perceptually Simple Transformations
  von: Kumar, Divyanshu, et al.
  Veröffentlicht: (2025)
• PrivTune: Efficient and Privacy-Preserving Fine-Tuning of Large Language Models via Device-Cloud Collaboration
  von: Liu, Yi, et al.
  Veröffentlicht: (2025)
• Medical MLLM is Vulnerable: Cross-Modality Jailbreak and Mismatched Attacks on Medical Multimodal Large Language Models
  von: Huang, Xijie, et al.
  Veröffentlicht: (2024)
• Structured Visual Narratives Undermine Safety Alignment in Multimodal Large Language Models
  von: Tan, Rui Yang, et al.
  Veröffentlicht: (2026)
• PRISM-XR: Empowering Privacy-Aware XR Collaboration with Multimodal Large Language Models
  von: Chen, Jiangong, et al.
  Veröffentlicht: (2026)