CodedPrivateML: A Fast and Privacy-Preserving Framework for Distributed Machine Learning
By Jinhyun So, Basak Guler, Amir Salman Avestimehr, Payman Mohassel. 2019
133 citations recorded by the source corpus.
How to train a machine learning model while keeping the data private and secure? We present CodedPrivateML, a fast and scalable approach to this critical problem. CodedPrivateML keeps both the data and the model information-theoretically private, while allowing efficient parallelization of training across distributed workers. We characterize CodedPrivateML’s privacy threshold and prove its convergence for logistic (and linear) regression. Furthermore, via extensive experiments on Amazon EC2, we demonstrate that CodedPrivateML provides significant speedup over cryptographic approaches based on multi-party computing (MPC).
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Basak Guler
- Amir Salman Avestimehr
- Jinhyun So
- Divya Gupta
- Nishanth Chandran
- Rahul Sharma
- Nishant Kumar
- Aseem Rastogi
Citations in the corpus
- Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learning (2020, methodology): “To do so, we leverage Lagrange coding [14], which has been applied to other problems such as offloading or collaborative machine learning in the privacy-preserving manner [47], [48].”
- CrypTFlow: Secure TensorFlow Inference (2019, result): “We also remark that there have been other recent works [54], [57], [5], [24], [20], [12], that modify the inference or training algorithms in order to obtain performance benefits.”
- A Scalable Approach for Privacy-Preserving Collaborative Machine Learning (2020, methodology): “Our encoding strategy utilizes Lagrange coding from [40]2, which has been applied to other problems such as privacy-preserving offloading of a training task [36] and secure federated learning [35].”