Search Results for author:
Found 3 papers, 3 papers with code
Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
The techniques of machine unlearning, also known as concept erasing, have been developed to address these risks.
Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning
This leads to the problem of machine unlearning (MU), aiming to eliminate the influence of chosen data points on model performance, while still maintaining the model's utility post-unlearning.
SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation
To address these challenges, we introduce the concept of 'weight saliency' for MU, drawing parallels with input saliency in model explanation.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
