Unleashing the Power of Pre-trained Encoders for Universal Adversarial Attack Detection

Documenti analoghi

• Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples
  di: Zhou, Ziqi, et al.
  Pubblicazione: (2024)
• MAA: Meticulous Adversarial Attack against Vision-Language Pre-trained Models
  di: Zhang, Peng-Fei, et al.
  Pubblicazione: (2025)
• Improving Generalizability and Undetectability for Targeted Adversarial Attacks on Multimodal Pre-trained Models
  di: Zhang, Zhifang, et al.
  Pubblicazione: (2025)
• Efficient and Effective Universal Adversarial Attack against Vision-Language Pre-training Models
  di: Yang, Fan, et al.
  Pubblicazione: (2024)
• VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models
  di: Yin, Ziyi, et al.
  Pubblicazione: (2024)