MaxModShift: Model Privacy via Designed Shifts
Not on the map. Why?
Abstract (arXiv)
Model learning by an eavesdropper is treated as an estimation problem in a federated environment. The Fisher Information Matrix for the eavesdropper's estimation problem is driven to singularity through a signaling design; this ensures that the eavesdropper cannot learn the model. Herein, the innovation of prior designs is that model shifts are designed to maximize the difference in the model learned by Eve and the central server while satisfying a transmission power constraint for the agents. Two shift schemes are provided. MaxModShift outperforms a prior ModShift design while requiring lesser transmission power. Compared to a noise injection scheme, MaxModShift performs better while requiring a lower bandwidth secret channel and a reduced average power consumption.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 10 of its 19 references that are in the map. First posted on arXiv 10 Aug 2026.
Builds on
10 of 19 references.
References · 10
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2019Advances and Open Problems in Federated Learningcited by 3,046
- 2016Deep Learning with Differential Privacycited by 2,728
- 2022FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correctioncited by 181
- 2022Privacy-Preserving Aggregation in Federated Learning: A Surveycited by 27
- 2023Channel State Information-Free Location-Privacy Enhancement: Fake Path Injectioncited by 5
- 2022Maximal Dissent: a State-Dependent Way to Agree in Distributed Convex Optimizationcited by 3
- 2023Guaranteed Private Communication with Secret Block Structurecited by 2
- 2025On Model Protection in Federated Learning against Eavesdropping Attackscited by 2
- 2025ModShift: Model Privacy via Designed Shiftscited by 1
Built on by
Not cited yet.