Machine Unlearning for Class Removal through SISA-based Deep Neural Network Architectures

TL;DR

This paper proposes a modified SISA framework with reinforcement and gating mechanisms to enable efficient class-level unlearning in CNNs, addressing data privacy concerns in AI models.

Contribution

It introduces a novel SISA-based architecture with enhancements for effective class unlearning without full retraining.

Findings

Effective class unlearning demonstrated across multiple datasets.

Model performance preserved while reducing retraining overhead.

Implementation available at https://github.com/SiamFS/sisa-class-unlearning.

Abstract

The rapid proliferation of image generation models and other artificial intelligence (AI) systems has intensified concerns regarding data privacy and user consent. As the availability of public datasets declines, major technology companies increasingly rely on proprietary or private user data for model training, raising ethical and legal challenges when users request the deletion of their data after it has influenced a trained model. Machine unlearning seeks to address this issue by enabling the removal of specific data from models without complete retraining. This study investigates a modified SISA (Sharded, Isolated, Sliced, and Aggregated) framework designed to achieve class-level unlearning in Convolutional Neural Network (CNN) architectures. The proposed framework incorporates a reinforced replay mechanism and a gating network to enhance selective forgetting efficiency. Experimental evaluations across multiple image datasets and CNN configurations demonstrate that the modified SISA approach enables effective class unlearning while preserving model performance and reducing retraining overhead. The findings highlight the potential of SISA-based unlearning for deployment in privacy-sensitive AI applications. The implementation is publicly available at https://github.com/SiamFS/ sisa-class-unlearning.