Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift

Ähnliche Einträge

• VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models
  von: Liang, Jiawei, et al.
  Veröffentlicht: (2024)
• BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning
  von: Liang, Siyuan, et al.
  Veröffentlicht: (2023)
• Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection
  von: Liang, Jiawei, et al.
  Veröffentlicht: (2024)
• Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack
  von: Zhu, Mingli, et al.
  Veröffentlicht: (2024)
• Adversarial Backdoor Defense in CLIP
  von: Kuang, Junhao, et al.
  Veröffentlicht: (2024)