mlsanityData to 7 Oct 2026

ModShift: Model Privacy via Designed Shifts

arXiv 2507.20060 ↗First posted 26 Jul 2025cs.LG cs.IT math.ITcited by 1

Not on the map. Why?

Abstract (arXiv)

In this paper, shifts are introduced to preserve model privacy against an eavesdropper in federated learning. Model learning is treated as a parameter estimation problem. This perspective allows us to derive the Fisher Information matrix of the model updates from the shifted updates and drive them to singularity, thus posing a hard estimation problem for Eve. The shifts are securely shared with the central server to maintain model accuracy at the server and participating devices. A convergence test is proposed to detect if model updates have been tampered with and we show that our scheme passes this test. Numerical results show that our scheme achieves a higher model shift when compared to a noise injection scheme while requiring a lesser bandwidth secret channel.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 13 of its 24 references that are in the map. First posted on arXiv 26 Jul 2025.

Builds on

13 of 24 references.

References · 13

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019Advances and Open Problems in Federated Learningcited by 3,021
  3. 2016Deep Learning with Differential Privacycited by 2,682
  4. 2022FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correctioncited by 181
  5. 2021LightSecAgg: a Lightweight and Versatile Design for Secure Aggregation in Federated Learningcited by 63
  6. 2020FastSecAgg: Scalable Secure Aggregation for Privacy-Preserving Federated Learningcited by 60
  7. 2022Privacy-Preserving Aggregation in Federated Learning: A Surveycited by 25
  8. 2020PrivFL: Practical Privacy-preserving Federated Regressions on High-dimensional Data over Mobile Networkscited by 10
  9. 2023Channel State Information-Free Location-Privacy Enhancement: Fake Path Injectioncited by 5
  10. 2022Maximal Dissent: a State-Dependent Way to Agree in Distributed Convex Optimizationcited by 3
  11. 2023Guaranteed Private Communication with Secret Block Structurecited by 2
  12. 2025On Model Protection in Federated Learning against Eavesdropping Attackscited by 2
1 more
  1. 2023Channel State Information-Free Location-Privacy Enhancement: Delay-Angle Information Spoofingcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026MaxModShift: Model Privacy via Designed Shiftscited by 0