Private Machine Learning in TensorFlow using Secure Computation
By Morten Dahl, Jason V. Mancuso, Yann Dupis, Ben Decoste, Morgan Giraud, Ian Livingstone, Justin Patriquin, Gavin Uhma. 2018
86 citations recorded by the source corpus.
We present a framework for experimenting with secure multi-party computation directly in TensorFlow. By doing so we benefit from several properties valuable to both researchers and practitioners, including tight integration with ordinary machine learning processes, existing optimizations for distributed computation in TensorFlow, high-level abstractions for expressing complex algorithms and protocols, and an expanded set of familiar tooling. We give an open source implementation of a state-of-the-art protocol and report on concrete benchmarks using typical models from private machine learning.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Marcel Keller
- Assi Barak
- Daniel E. Escudero
- Nishant Kumar
- Anders Dalskov
- Mayank Rathee
- Nishanth Chandran
- Divya Gupta
Citations in the corpus
- Secure Evaluation of Quantized Neural Networks (2019, background): “Several solutions have also been developed by researchers closer to the industry side, such as TFEncrypted [16] or CrypTen [25], which suggests that secure prediction has value beyond the academic point of view—an important factor for accelerating wide adoption of these techniques.”
- A Scalable Approach for Privacy-Preserving Collaborative Machine Learning (2020, unknown): “…we empirically demonstrate the performance of COPML by comparing it with cryptographic benchmarks based on secure multi-party computing (MPC) [1], [2], [3], [4], that can also be applied to enable privacy-preserving machine learning tasks (e.g. see [5], [6], [7], [8], [9], [10], [11], [12]).”
- Benchmarking Differentially Private Residual Networks for Medical Imagery (2020, unknown): “Research related towards implementation techniques for secure deep learning include (Ryffel et al.; Dahl et al., 2018).”
- CodedPrivateML: A Fast and Privacy-Preserving Framework for Distributed Machine Learning (2019, unknown): “see (Nikolaenko et al., 2013; Gascón et al., 2017; Mohassel & Zhang, 2017; Lindell & Pinkas, 2000; Dahl et al., 2018; Chen et al., 2019)).”
- CrypTFlow: Secure TensorFlow Inference (2019, background): “and TF-Encrypted [26] are ongoing efforts that also aim to compile DNNs to MPC protocols.”