Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.27804 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914520773951488 |
|---|---|
| author | Mahi, Ishrak Hamim Ferdous, Siam Badhon, Md Sakib Sadman Omi, Nabid Hasan Hemel, Md Habibun Nabi Sadeque, Farig Yousuf Reza, Md. Tanzim |
| author_facet | Mahi, Ishrak Hamim Ferdous, Siam Badhon, Md Sakib Sadman Omi, Nabid Hasan Hemel, Md Habibun Nabi Sadeque, Farig Yousuf Reza, Md. Tanzim |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_27804 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Machine Unlearning for Class Removal through SISA-based Deep Neural Network Architectures Mahi, Ishrak Hamim Ferdous, Siam Badhon, Md Sakib Sadman Omi, Nabid Hasan Hemel, Md Habibun Nabi Sadeque, Farig Yousuf Reza, Md. Tanzim Computer Vision and Pattern Recognition Cryptography and Security Machine Learning 68T05, 68T07 I.2.6; I.5.1; K.4.1 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. |
| title | Machine Unlearning for Class Removal through SISA-based Deep Neural Network Architectures |
| topic | Computer Vision and Pattern Recognition Cryptography and Security Machine Learning 68T05, 68T07 I.2.6; I.5.1; K.4.1 |
| url | https://arxiv.org/abs/2604.27804 |