Summary of Deep Learning with Data Privacy Via Residual Perturbation, by Wenqi Tao et al.
Deep Learning with Data Privacy via Residual Perturbation
by Wenqi Tao, Huaming Ling, Zuoqiang Shi, Bao Wang
First submitted to arxiv on: 11 Aug 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Cryptography and Security (cs.CR); 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 stochastic differential equation-based residual perturbation for privacy-preserving deep learning injects Gaussian noise into each residual mapping of ResNets, theoretically guaranteeing differential privacy and reducing the generalization gap. The method outperforms state-of-the-art differentially private stochastic gradient descent in utility maintenance without sacrificing membership privacy. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper proposes a new way to keep data private when using deep learning algorithms. It adds noise to each layer of a neural network, ensuring that sensitive information remains protected. This approach is efficient and effective, outperforming current methods while maintaining high levels of privacy. |
Keywords
» Artificial intelligence » Deep learning » Generalization » Neural network » Stochastic gradient descent
