PRUNE: A Patching Based Repair Framework for Certifiable Unlearning of Neural Networks

Documenti analoghi

• Unlearning Inversion Attacks for Graph Neural Networks
  di: Zhang, Jiahao, et al.
  Pubblicazione: (2025)
• AuditVotes: A Framework Towards More Deployable Certified Robustness for Graph Neural Networks
  di: Lai, Yuni, et al.
  Pubblicazione: (2025)
• Rounding-Guided Backdoor Injection in Deep Learning Model Quantization
  di: Chen, Xiangxiang, et al.
  Pubblicazione: (2025)
• FairProof : Confidential and Certifiable Fairness for Neural Networks
  di: Yadav, Chhavi, et al.
  Pubblicazione: (2024)
• Certified Unlearning for Neural Networks
  di: Koloskova, Anastasia, et al.
  Pubblicazione: (2025)