Backdoor Unlearning by Linear Task Decomposition

Documenti analoghi

• LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging
  di: Wang, Ke, et al.
  Pubblicazione: (2024)
• Localizing Task Information for Improved Model Merging and Compression
  di: Wang, Ke, et al.
  Pubblicazione: (2024)
• Using Interleaved Ensemble Unlearning to Keep Backdoors at Bay for Finetuning Vision Transformers
  di: Li, Zeyu Michael
  Pubblicazione: (2024)
• Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness
  di: Lin, Weilin, et al.
  Pubblicazione: (2024)
• Sequential Representation Learning via Static-Dynamic Conditional Disentanglement
  di: Simon, Mathieu Cyrille, et al.
  Pubblicazione: (2024)