Attack and Reset for Unlearning: Exploiting Adversarial Noise toward Machine Unlearning through Parameter Re-initialization

Documenti analoghi

• ViT-MUL: A Baseline Study on Recent Machine Unlearning Methods Applied to Vision Transformers
  di: Cho, Ikhyun, et al.
  Pubblicazione: (2024)
• ZIUM: Zero-Shot Intent-Aware Adversarial Attack on Unlearned Models
  di: Yook, Hyun Jun, et al.
  Pubblicazione: (2025)
• DeepClean: Machine Unlearning on the Cheap by Resetting Privacy Sensitive Weights using the Fisher Diagonal
  di: Shi, Jiaeli, et al.
  Pubblicazione: (2023)
• UnlearnShield: Shielding Forgotten Privacy against Unlearning Inversion
  di: Xue, Lulu, et al.
  Pubblicazione: (2026)
• Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
  di: Zhang, Yimeng, et al.
  Pubblicazione: (2024)