# MaxModShift: Model Privacy via Designed Shifts

arXiv: https://arxiv.org/abs/2608.09328 · HTML: https://mlsanity.com/paper/2608.09328/

## 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 (most cited first, 10 of 10)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correction](https://mlsanity.com/paper/2203.11751/) (2022)
- [Privacy-Preserving Aggregation in Federated Learning: A Survey](https://mlsanity.com/paper/2203.17005/) (2022)
- [Channel State Information-Free Location-Privacy Enhancement: Fake Path Injection](https://mlsanity.com/paper/2307.05442/) (2023)
- [Maximal Dissent: a State-Dependent Way to Agree in Distributed Convex Optimization](https://mlsanity.com/paper/2205.00647/) (2022)
- [Guaranteed Private Communication with Secret Block Structure](https://mlsanity.com/paper/2309.12949/) (2023)
- [On Model Protection in Federated Learning against Eavesdropping Attacks](https://mlsanity.com/paper/2504.02114/) (2025)
- [ModShift: Model Privacy via Designed Shifts](https://mlsanity.com/paper/2507.20060/) (2025)

## 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.