mlsanityData to 7 Oct 2026

Privacy-Preserving Federated Learning via Homomorphic Adversarial Networks

arXiv 2412.01650 ↗First posted 2 Dec 2024cs.CR cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Privacy-preserving federated learning (PPFL) aims to train a global model for multiple clients while maintaining their data privacy. However, current PPFL protocols exhibit one or more of the following insufficiencies: considerable degradation in accuracy, the requirement for sharing keys, and cooperation during the key generation or decryption processes. As a mitigation, we develop the first protocol that utilizes neural networks to implement PPFL, as well as incorporating an Aggregatable Hybrid Encryption scheme tailored to the needs of PPFL. We name these networks as Homomorphic Adversarial Networks (HANs) which demonstrate that neural networks are capable of performing tasks similar to multi-key homomorphic encryption (MK-HE) while solving the problems of key distribution and collaborative decryption. Our experiments show that HANs are robust against privacy attacks. Compared with non-private federated learning, experiments conducted on multiple datasets demonstrate that HANs exhibit a negligible accuracy loss (at most 1.35%). Compared to traditional MK-HE schemes, HANs increase encryption aggregation speed by 6,075 times while incurring a 29.2 times increase in communication overhead.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 20 of its 44 references that are in the map. First posted on arXiv 2 Dec 2024.

Builds on

20 of 44 references.

References · 20

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  3. 2016Deep Learning with Differential Privacycited by 2,682
  4. 2019Deep Leakage from Gradientscited by 1,004
  5. 2021Membership Inference Attacks From First Principlescited by 839
  6. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  7. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 558
  8. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 528
  9. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
  10. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 451
  11. 2019A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protectioncited by 371
  12. 2020iDLG: Improved Deep Leakage from Gradientscited by 367
8 more
  1. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 326
  2. 2019FedHealth: A Federated Transfer Learning Framework for Wearable Healthcarecited by 182
  3. 2019Federated Learning with Bayesian Differential Privacycited by 60
  4. 2021Privacy-preserving Federated Learning based on Multi-key Homomorphic Encryptioncited by 46
  5. 2021Federated Learning with Local Differential Privacy: Trade-offs between Privacy, Utility, and Communicationcited by 38
  6. 2016Learning to Protect Communications with Adversarial Neural Cryptographycited by 11
  7. 2022Homomorphic Encryption and Federated Learning based Privacy-Preserving CNN Training: COVID-19 Detection Use-Casecited by 11
  8. 2022Encrypted Semantic Communication Using Adversarial Training for Privacy Preservingcited by 10

Built on by

Not cited yet.