mlsanityData to 14 Oct 2026

Efficient Deep Learning on Multi-Source Private Data

arXiv 1807.06689 ↗First posted 17 Jul 2018cs.LG stat.MLcited by 17

Not on the map. Why?

Abstract (arXiv)

Machine learning models benefit from large and diverse datasets. Using such datasets, however, often requires trusting a centralized data aggregator. For sensitive applications like healthcare and finance this is undesirable as it could compromise patient privacy or divulge trade secrets. Recent advances in secure and privacy-preserving computation, including trusted hardware enclaves and differential privacy, offer a way for mutually distrusting parties to efficiently train a machine learning model without revealing the training data. In this work, we introduce Myelin, a deep learning framework which combines these privacy-preservation primitives, and use it to establish a baseline level of performance for fully private machine learning.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). First posted on arXiv 17 Jul 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 7; 2022: 6; 2023: 2; 2024: 1; 2025: 0; 2026: 1.

17 papers.

Sort:

By area:

  1. 2021Opacus: User-Friendly Differential Privacy Library in PyTorchcited by 383
  2. 2023Privacy and Fairness in Federated Learning: on the Perspective of Trade-offcited by 26
  3. 2022Machine Learning with Confidential Computing: A Systematization of Knowledgecited by 15
  4. 2022Proof of Unlearning: Definitions and Instantiationcited by 15
  5. 2021Citadel: Protecting Data Privacy and Model Confidentiality for Collaborative Learning with SGXcited by 14
  6. 2022DarKnight: An Accelerated Framework for Privacy and Integrity Preserving Deep Learning Using Trusted Hardwarecited by 14
  7. 2022Decentralized Stochastic Optimization with Inherent Privacy Protectioncited by 11
  8. 2023Blockchain-based Federated Learning with Secure Aggregation in Trusted Execution Environment for Internet-of-Thingscited by 10
  9. 2021Separation of Powers in Federated Learningcited by 8
  10. 2022Quantization enabled Privacy Protection in Decentralized Stochastic Optimizationcited by 7
  11. 2021Confidential Machine Learning Computation in Untrusted Environments: A Systems Security Perspectivecited by 4
  12. 2026Proof-of-Guardrail in AI Agents and What (Not) to Trust from Itcited by 4
5 more
  1. 2021Plinius: Secure and Persistent Machine Learning Model Trainingcited by 3
  2. 2022Predictive Crypto-Asset Automated Market Making Architecture for Decentralized Finance using Deep Reinforcement Learningcited by 1
  3. 2021Privacy and Integrity Preserving Training Using Trusted Hardwarecited by 0
  4. 2021Secure Machine Learning in the Cloud Using One Way Scrambling by Deconvolutioncited by 0
  5. 2024Protecting Confidentiality, Privacy and Integrity in Collaborative Learningcited by 0