Wildest Dreams: Reproducible Research in Privacy-preserving Neural Network Training
Not on the map. Why?
Abstract (arXiv)
Machine Learning (ML), addresses a multitude of complex issues in multiple disciplines, including social sciences, finance, and medical research. ML models require substantial computing power and are only as powerful as the data utilized. Due to high computational cost of ML methods, data scientists frequently use Machine Learning-as-a-Service (MLaaS) to outsource computation to external servers. However, when working with private information, like financial data or health records, outsourcing the computation might result in privacy issues. Recent advances in Privacy-Preserving Techniques (PPTs) have enabled ML training and inference over protected data through the use of Privacy-Preserving Machine Learning (PPML). However, these techniques are still at a preliminary stage and their application in real-world situations is demanding. In order to comprehend discrepancy between theoretical research suggestions and actual applications, this work examines the past and present of PPML, focusing on Homomorphic Encryption (HE) and Secure Multi-party Computation (SMPC) applied to ML. This work primarily focuses on the ML model's training phase, where maintaining user data privacy is of utmost importance. We provide a solid theoretical background that eases the understanding of current approaches and their limitations. In addition, we present a SoK of the most recent PPML frameworks for model training and provide a comprehensive comparison in terms of the unique properties and performances on standard benchmarks. Also, we reproduce the results for some of the papers and examine at what level existing works in the field provide support for open science. We believe our work serves as a valuable contribution by raising awareness about the current gap between theoretical advancements and real-world applications in PPML, specifically regarding open-source availability, reproducibility, and usability.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 34 of its 140 references that are in the map. First posted on arXiv 6 Mar 2024.
Builds on
34 of 140 references.
References · 34
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
- 2015Character-level Convolutional Networks for Text Classificationcited by 2,330
- 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
- 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 334
- 2018Distributed learning of deep neural network over multiple agentscited by 279
- 2018A Hybrid Approach to Privacy-Preserving Federated Learningcited by 210
- 2017A Survey on Homomorphic Encryption Schemes: Theory and Implementationcited by 156
- 2021CrypTen: Secure Multi-Party Computation Meets Machine Learningcited by 131
- 2020Unleashing the Tiger: Inference Attacks on Split Learningcited by 105
- 2021Label Leakage and Protection in Two-party Split Learningcited by 90
- 2020FALCON: Honest-Majority Maliciously Secure Framework for Private Deep Learningcited by 74
22 more
- 2021Privacy-Preserving Machine Learning: Methods, Challenges and Directionscited by 58
- 2020Can We Use Split Learning on 1D CNN Models for Privacy Preserving Training?cited by 50
- 2017DeepSecure: Scalable Provably-Secure Deep Learningcited by 48
- 2021CryptGPU: Fast Privacy-Preserving Machine Learning on the GPUcited by 46
- 2019QUOTIENT: Two-Party Secure Neural Network Training and Predictioncited by 41
- 2021CaPC Learning: Confidential and Private Collaborative Learningcited by 33
- 2020BLAZE: Blazing Fast Privacy-Preserving Machine Learningcited by 32
- 2019Trident: Efficient 4PC Framework for Privacy Preserving Machine Learningcited by 26
- 2020POSEIDON: Privacy-Preserving Federated Neural Network Learningcited by 24
- 2020SWIFT: Super-fast and Robust Privacy-Preserving Machine Learningcited by 20
- 2020ARIANN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret Sharingcited by 20
- 2018Private Machine Learning in TensorFlow using Secure Computationcited by 15
- 2023Split Ways: Privacy-Preserving Training of Encrypted Data Using Split Learningcited by 15
- 2019PrivFT: Private and Fast Text Classification with Homomorphic Encryptioncited by 12
- 2021Blind Faith: Privacy-Preserving Machine Learning using Function Approximationcited by 10
- 2021SoK: Fully Homomorphic Encryption Compilerscited by 9
- 2024GuardML: Efficient Privacy-Preserving Machine Learning Services Through Hybrid Homomorphic Encryptioncited by 7
- 2020Neural Network Training With Homomorphic Encryptioncited by 6
- 2023Learning in the Dark: Privacy-Preserving Machine Learning using Function Approximationcited by 6
- 2023A More Secure Split: Enhancing the Security of Privacy-Preserving Split Learningcited by 5
- 2021Adam in Private: Secure and Fast Training of Deep Neural Networks with Adaptive Moment Estimationcited by 4
- 2021MPCLeague: Robust MPC Platform for Privacy-Preserving Machine Learningcited by 3
Built on by
Citing papers per year: 2024: 2.
2 papers.