CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning

Documenti analoghi

• Hide in Plain Sight: Clean-Label Backdoor for Auditing Membership Inference
  di: Chen, Depeng, et al.
  Pubblicazione: (2024)
• On Membership Inference Attacks in Knowledge Distillation
  di: Cui, Ziyao, et al.
  Pubblicazione: (2025)
• Membership Inference Attack with Partial Features
  di: Wang, Xurun, et al.
  Pubblicazione: (2025)
• Center-Based Relaxed Learning Against Membership Inference Attacks
  di: Fang, Xingli, et al.
  Pubblicazione: (2024)
• Learning-Based Difficulty Calibration for Enhanced Membership Inference Attacks
  di: Shi, Haonan, et al.
  Pubblicazione: (2024)