Robust Defense Strategies for Multimodal Contrastive Learning: Efficient Fine-tuning Against Backdoor Attacks

Documenti analoghi

• Variance-Based Defense Against Blended Backdoor Attacks
  di: Aseervatham, Sujeevan, et al.
  Pubblicazione: (2025)
• Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearning
  di: Liang, Siyuan, et al.
  Pubblicazione: (2024)
• BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning
  di: Liang, Siyuan, et al.
  Pubblicazione: (2023)
• Securing Vision-Language Models with a Robust Encoder Against Jailbreak and Adversarial Attacks
  di: Hossain, Md Zarif, et al.
  Pubblicazione: (2024)
• CleanerCLIP: Fine-grained Counterfactual Semantic Augmentation for Backdoor Defense in Contrastive Learning
  di: Xun, Yuan, et al.
  Pubblicazione: (2024)