Machine unlearning via GAN
This addresses data privacy concerns for users and organizations by enabling efficient machine unlearning, though it is incremental as it builds on existing GAN and unlearning methods.
The paper tackles the problem of removing specific training data from deep learning models to comply with privacy regulations like GDPR, using a GAN-based algorithm that significantly speeds up deletion compared to retraining from scratch, as demonstrated on five datasets.
Machine learning models, especially deep models, may unintentionally remember information about their training data. Malicious attackers can thus pilfer some property about training data by attacking the model via membership inference attack or model inversion attack. Some regulations, such as the EU's GDPR, have enacted "The Right to Be Forgotten" to protect users' data privacy, enhancing individuals' sovereignty over their data. Therefore, removing training data information from a trained model has become a critical issue. In this paper, we present a GAN-based algorithm to delete data in deep models, which significantly improves deleting speed compared to retraining from scratch, especially in complicated scenarios. We have experimented on five commonly used datasets, and the experimental results show the efficiency of our method.