# Privacy-Preserving Debiasing using Data Augmentation and Machine Unlearning

arXiv: https://arxiv.org/abs/2404.13194 · HTML: https://mlsanity.com/paper/2404.13194/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 9 of its 19 references that are in the map.
- First posted on arXiv 19 Apr 2024.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 9 of 9)

- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Remember What You Want to Forget: Algorithms for Machine Unlearning](https://mlsanity.com/paper/2103.03279/) (2021)
- [Membership Inference Attacks on Machine Learning: A Survey](https://mlsanity.com/paper/2103.07853/) (2021)
- [When Machine Unlearning Jeopardizes Privacy](https://mlsanity.com/paper/2005.02205/) (2020)
- [Privacy Risks of Securing Machine Learning Models against Adversarial Examples](https://mlsanity.com/paper/1905.10291/) (2019)
- [Synthetic Data Augmentation using GAN for Improved Liver Lesion Classification](https://mlsanity.com/paper/1801.02385/) (2018)
- [BAGAN: Data Augmentation with Balancing GAN](https://mlsanity.com/paper/1803.09655/) (2018)
- [On the Effectiveness of Regularization Against Membership Inference Attacks](https://mlsanity.com/paper/2006.05336/) (2020)
- [Information Theoretic Measures for Fairness-aware Feature Selection](https://mlsanity.com/paper/2106.00772/) (2021)

## Abstract (arXiv)

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.