Towards Adversarial Evaluations for Inexact Machine Unlearning
Machine Learning models face increased concerns regarding the storage of personal user data and adverse impacts of corrupted data like backdoors or systematic bias. Machine Unlearning can address these by allowing post-hoc deletion of affected training data from a learned model. Achieving this task exactly is computationally expensive; consequently, recent works have proposed inexact unlearning algorithms to solve this approximately as well as evaluation methods to test the effectiveness of these algorithms. In this work, we first outline some necessary criteria for evaluation methods and show no existing evaluation satisfies them all. Then, we design a stronger black-box evaluation method called the Interclass Confusion (IC) test which adversarially manipulates data during training to detect the insufficiency of unlearning procedures. We also propose two analytically motivated baseline methods~(EU-k and CF-k) which outperform several popular inexact unlearning methods. Overall, we demonstrate how adversarial evaluation strategies can help in analyzing various unlearning phenomena which can guide the development of stronger unlearning algorithms.
Code (3)
Tasks
Machine UnlearningMemorizationSimilar Papers 제목 키워드 기반
Rectifying Privacy and Efficacy Measurements in Machine Unlearning: A New Inference Attack Perspective
Machine unlearning focuses on efficiently removing specific data from trained models, addressing privacy and compliance concerns with reasonable costs. Although exact unlearning ensures complete data removal equivalent t…
Inference AttackMachine UnlearningMachine unlearning through fine-grained model parameters perturbation
Machine unlearning techniques, which involve retracting data records and reducing influence of said data on trained models, help with the user privacy protection objective but incur significant computational costs. Weigh…
Machine UnlearningmodelGone but Not Forgotten: Improved Benchmarks for Machine Unlearning
Machine learning models are vulnerable to adversarial attacks, including attacks that leak information about the model's training data. There has recently been an increase in interest about how to best address privacy co…
Machine UnlearningWSS-CL: Weight Saliency Soft-Guided Contrastive Learning for Efficient Machine Unlearning Image Classification
Machine unlearning, the efficient deletion of the impact of specific data in a trained model, remains a challenging problem. Current machine unlearning approaches that focus primarily on data-centric or weight-based stra…
Contrastive LearningImage ClassificationUnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI
Exact unlearning was first introduced as a privacy mechanism that allowed a user to retract their data from machine learning models on request. Shortly after, inexact schemes were proposed to mitigate the impractical cos…
In-Context Learning