Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attacks

Documenti analoghi

• TweezeEdit: Consistent and Efficient Image Editing with Path Regularization
  di: Mao, Jianda, et al.
  Pubblicazione: (2025)
• Large Language Model with Region-guided Referring and Grounding for CT Report Generation
  di: Chen, Zhixuan, et al.
  Pubblicazione: (2024)
• Dia-LLaMA: Towards Large Language Model-driven CT Report Generation
  di: Chen, Zhixuan, et al.
  Pubblicazione: (2024)
• Securing Vision-Language Models with a Robust Encoder Against Jailbreak and Adversarial Attacks
  di: Hossain, Md Zarif, et al.
  Pubblicazione: (2024)
• Robust Vision-Language Models via Tensor Decomposition: A Defense Against Adversarial Attacks
  di: Patel, Het, et al.
  Pubblicazione: (2025)