Label Leakage Attacks in Machine Unlearning: A Parameter and Inversion-Based Approach

Documenti analoghi

• Classification-Head Bias in Class-Level Machine Unlearning: Diagnosis, Mitigation, and Evaluation
  di: Zheng, Weidong, et al.
  Pubblicazione: (2026)
• EdgeLeakage: Membership Information Leakage in Distributed Edge Intelligence Systems
  di: Chen, Kongyang, et al.
  Pubblicazione: (2024)
• Membership Information Leakage in Federated Contrastive Learning
  di: Chen, Kongyang, et al.
  Pubblicazione: (2024)
• Learn What You Want to Unlearn: Unlearning Inversion Attacks against Machine Unlearning
  di: Hu, Hongsheng, et al.
  Pubblicazione: (2024)
• Machine Unlearning in Large Language Models
  di: Chen, Kongyang, et al.
  Pubblicazione: (2024)