Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples

Documenti analoghi

• Secure Transfer Learning: Training Clean Models Against Backdoor in (Both) Pre-trained Encoders and Downstream Datasets
  di: Zhang, Yechao, et al.
  Pubblicazione: (2025)
• SegTrans: Transferable Adversarial Examples for Segmentation Models
  di: Song, Yufei, et al.
  Pubblicazione: (2025)
• Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability
  di: Zhang, Yechao, et al.
  Pubblicazione: (2023)
• Transferable Physical-World Adversarial Patches Against Object Detection in Autonomous Driving
  di: Zhu, Zihui, et al.
  Pubblicazione: (2026)
• DarkHash: A Data-Free Backdoor Attack Against Deep Hashing
  di: Zhou, Ziqi, et al.
  Pubblicazione: (2025)