Backdooring Vision-Language Models with Out-Of-Distribution Data

Documenti analoghi

• TrojVLM: Backdoor Attack Against Vision Language Models
  di: Lyu, Weimin, et al.
  Pubblicazione: (2024)
• Long-Tailed Backdoor Attack Using Dynamic Data Augmentation Operations
  di: Pang, Lu, et al.
  Pubblicazione: (2024)
• Mask and Restore: Blind Backdoor Defense at Test Time with Masked Autoencoder
  di: Sun, Tao, et al.
  Pubblicazione: (2023)
• Unrolled Networks are Conditional Probability Flows in MRI Reconstruction
  di: Qi, Kehan, et al.
  Pubblicazione: (2025)
• LoC-Path: Learning to Compress for Pathology Multimodal Large Language Models
  di: Hu, Qingqiao, et al.
  Pubblicazione: (2025)