Summary of Privacy-preserving Debiasing Using Data Augmentation and Machine Unlearning, by Zhixin Pan et al.
Privacy-Preserving Debiasing using Data Augmentation and Machine Unlearning
by Zhixin Pan, Emma Andrews, Laura Chang, Prabhat Mishra
First submitted to arxiv on: 19 Apr 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed combination of data augmentation and machine unlearning effectively reduces data bias while providing a provable defense against known membership inference attacks. The approach maintains fairness through diffusion-based data augmentation, followed by multi-shard unlearning to remove identifying information from the model. This hybrid method demonstrates significant improvements in both bias reduction and robustness against state-of-the-art privacy attacks across diverse datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper proposes a new way to make machine learning models fairer and more private. The idea is to combine two techniques: data augmentation, which helps remove biases in training data, and machine unlearning, which removes sensitive information from the model itself. This combined approach can help reduce biases in trained models while also protecting them against privacy attacks. The results show that this method works well on various datasets and can improve both fairness and privacy. |
Keywords
» Artificial intelligence » Data augmentation » Diffusion » Inference » Machine learning
