Privacy-Preserving Debiasing using Data Augmentation and Machine Unlearning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909176152719360 |
|---|---|
| author | Pan, Zhixin Andrews, Emma Chang, Laura Mishra, Prabhat |
| author_facet | Pan, Zhixin Andrews, Emma Chang, Laura Mishra, Prabhat |
| contents | Data augmentation is widely used to mitigate data bias in the training dataset. However, data augmentation exposes machine learning models to privacy attacks, such as membership inference attacks. In this paper, we propose an effective combination of data augmentation and machine unlearning, which can reduce data bias while providing a provable defense against known attacks. Specifically, we maintain the fairness of the trained model with diffusion-based data augmentation, and then utilize multi-shard unlearning to remove identifying information of original data from the ML model for protection against privacy attacks. Experimental evaluation across diverse datasets demonstrates that our approach can achieve significant improvements in bias reduction as well as robustness against state-of-the-art privacy attacks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_13194 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Privacy-Preserving Debiasing using Data Augmentation and Machine Unlearning Pan, Zhixin Andrews, Emma Chang, Laura Mishra, Prabhat Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Data augmentation is widely used to mitigate data bias in the training dataset. However, data augmentation exposes machine learning models to privacy attacks, such as membership inference attacks. In this paper, we propose an effective combination of data augmentation and machine unlearning, which can reduce data bias while providing a provable defense against known attacks. Specifically, we maintain the fairness of the trained model with diffusion-based data augmentation, and then utilize multi-shard unlearning to remove identifying information of original data from the ML model for protection against privacy attacks. Experimental evaluation across diverse datasets demonstrates that our approach can achieve significant improvements in bias reduction as well as robustness against state-of-the-art privacy attacks. |
| title | Privacy-Preserving Debiasing using Data Augmentation and Machine Unlearning |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.13194 |