Documenti analoghi

• Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuning
  di: Zhang, Zhifang, et al.
  Pubblicazione: (2024)
• Candidate Pseudolabel Learning: Enhancing Vision-Language Models by Prompt Tuning with Unlabeled Data
  di: Zhang, Jiahan, et al.
  Pubblicazione: (2024)
• Unleashing the Power of Pre-trained Encoders for Universal Adversarial Attack Detection
  di: Zhang, Yinghe, et al.
  Pubblicazione: (2025)
• VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models
  di: Yin, Ziyi, et al.
  Pubblicazione: (2023)
• Enhancing Adversarial Attacks: The Similar Target Method
  di: Zhang, Shuo, et al.
  Pubblicazione: (2023)