Private Machine Learning in TensorFlow using Secure Computation
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Oct 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 7; 2022: 3; 2023: 1; 2024: 1; 2025: 2; 2026: 1.
15 papers.
Sort:
- 2021Secure Quantized Training for Deep Learningcited by 15
- 2022Private, Efficient, and Accurate: Protecting Models Trained by Multi-party Learning with Differential Privacycited by 7
- 2025Differential privacy for medical deep learning: methods, tradeoffs, and deployment implicationscited by 7
- 2021Enabling Homomorphically Encrypted Inference for Large DNN Modelscited by 6
- 2021Evaluating Privacy-Preserving Machine Learning in Critical Infrastructures: A Case Study on Time-Series Classificationcited by 6
- 2022Hijack Vertical Federated Learning Models As One Partycited by 4
- 2022Efficient ML Models for Practical Secure Inferencecited by 2
- 2023XAI for time-series classification leveraging image highlight methodscited by 2
- 2024Wildest Dreams: Reproducible Research in Privacy-preserving Neural Network Trainingcited by 2
- 2021Efficient CNN Building Blocks for Encrypted Datacited by 1
- 2021Privacy-preserving Machine Learning for Medical Image Classificationcited by 1
- 2025Covert Attacks on Machine Learning Training in Passively Secure MPCcited by 1
- 2026MPC-Patch-Bench: Security-Aware LLM Code Patch for Multi-Party Computation9 Jun 2026
- 2025Differential privacy for medical deep learning: methods, tradeoffs, and deployment implications31 May 2025
- 2025Covert Attacks on Machine Learning Training in Passively Secure MPC21 May 2025
- 2024Wildest Dreams: Reproducible Research in Privacy-preserving Neural Network Training6 Mar 2024
- 2023XAI for time-series classification leveraging image highlight methods28 Nov 2023
- 2022Hijack Vertical Federated Learning Models As One Party1 Dec 2022
- 2022Efficient ML Models for Practical Secure Inference26 Aug 2022
- 2022Private, Efficient, and Accurate: Protecting Models Trained by Multi-party Learning with Differential Privacy18 Aug 2022
- 2021Evaluating Privacy-Preserving Machine Learning in Critical Infrastructures: A Case Study on Time-Series Classification29 Nov 2021
- 2021Towards General-purpose Infrastructure for Protecting Scientific Data Under Study4 Oct 2021
- 2021Morse-STF: Improved Protocols for Privacy-Preserving Machine Learning24 Sep 2021
- 2021Privacy-preserving Machine Learning for Medical Image Classification29 Aug 2021
3 more
- 2021Secure Quantized Training for Deep Learning1 Jul 2021
- 2021Enabling Homomorphically Encrypted Inference for Large DNN Models30 Mar 2021
- 2021Efficient CNN Building Blocks for Encrypted Data30 Jan 2021
- 2021Secure Quantized Training for Deep Learningcited by 15
- 2022Private, Efficient, and Accurate: Protecting Models Trained by Multi-party Learning with Differential Privacycited by 7
- 2025Differential privacy for medical deep learning: methods, tradeoffs, and deployment implicationscited by 7
- 2021Enabling Homomorphically Encrypted Inference for Large DNN Modelscited by 6
- 2021Evaluating Privacy-Preserving Machine Learning in Critical Infrastructures: A Case Study on Time-Series Classificationcited by 6
- 2022Hijack Vertical Federated Learning Models As One Partycited by 4
- 2022Efficient ML Models for Practical Secure Inferencecited by 2
- 2023XAI for time-series classification leveraging image highlight methodscited by 2
- 2024Wildest Dreams: Reproducible Research in Privacy-preserving Neural Network Trainingcited by 2
- 2021Efficient CNN Building Blocks for Encrypted Datacited by 1
- 2021Privacy-preserving Machine Learning for Medical Image Classificationcited by 1
- 2025Covert Attacks on Machine Learning Training in Passively Secure MPCcited by 1
12 most cited of 15 All 15 (JSON)
- 2026MPC-Patch-Bench: Security-Aware LLM Code Patch for Multi-Party Computation9 Jun 2026
- 2025Differential privacy for medical deep learning: methods, tradeoffs, and deployment implications31 May 2025
- 2025Covert Attacks on Machine Learning Training in Passively Secure MPC21 May 2025
- 2024Wildest Dreams: Reproducible Research in Privacy-preserving Neural Network Training6 Mar 2024
- 2023XAI for time-series classification leveraging image highlight methods28 Nov 2023
- 2022Hijack Vertical Federated Learning Models As One Party1 Dec 2022
- 2022Efficient ML Models for Practical Secure Inference26 Aug 2022
- 2022Private, Efficient, and Accurate: Protecting Models Trained by Multi-party Learning with Differential Privacy18 Aug 2022
- 2021Evaluating Privacy-Preserving Machine Learning in Critical Infrastructures: A Case Study on Time-Series Classification29 Nov 2021
- 2021Towards General-purpose Infrastructure for Protecting Scientific Data Under Study4 Oct 2021
- 2021Morse-STF: Improved Protocols for Privacy-Preserving Machine Learning24 Sep 2021
- 2021Privacy-preserving Machine Learning for Medical Image Classification29 Aug 2021
12 newest of 15 All 15 (JSON)