# On Model Protection in Federated Learning against Eavesdropping Attacks

arXiv: https://arxiv.org/abs/2504.02114 · HTML: https://mlsanity.com/paper/2504.02114/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 47 references that are in the map.
- First posted on arXiv 2 Apr 2025.

## Builds on (most cited first, 29 of 29)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Deep Leakage from Gradients](https://mlsanity.com/paper/1906.08935/) (2019)
- [Towards Federated Learning at Scale: System Design](https://mlsanity.com/paper/1902.01046/) (2019)
- [Inverting Gradients -- How easy is it to break privacy in federated learning?](https://mlsanity.com/paper/2003.14053/) (2020)
- [Federated Multi-Task Learning](https://mlsanity.com/paper/1705.10467/) (2017)
- [Stealing Machine Learning Models via Prediction APIs](https://mlsanity.com/paper/1609.02943/) (2016)
- [Federated Optimization: Distributed Machine Learning for On-Device Intelligence](https://mlsanity.com/paper/1610.02527/) (2016)
- [Federated Learning Based on Dynamic Regularization](https://mlsanity.com/paper/2111.04263/) (2021)
- [Federated Learning with Differential Privacy: Algorithms and Performance Analysis](https://mlsanity.com/paper/1911.00222/) (2019)
- [Robust and Communication-Efficient Federated Learning from Non-IID Data](https://mlsanity.com/paper/1903.02891/) (2019)
- [iDLG: Improved Deep Leakage from Gradients](https://mlsanity.com/paper/2001.02610/) (2020)
- [A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection](https://mlsanity.com/paper/1907.09693/) (2019)
- [Data Poisoning Attacks Against Federated Learning Systems](https://mlsanity.com/paper/2007.08432/) (2020)
- [Federated Learning for Smart Healthcare: A Survey](https://mlsanity.com/paper/2111.08834/) (2021)
- [FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correction](https://mlsanity.com/paper/2203.11751/) (2022)
- [Privacy and Robustness in Federated Learning: Attacks and Defenses](https://mlsanity.com/paper/2012.06337/) (2020)
- [Protection Against Reconstruction and Its Applications in Private Federated Learning](https://mlsanity.com/paper/1812.00984/) (2018)
- [FedDANE: A Federated Newton-Type Method](https://mlsanity.com/paper/2001.01920/) (2020)
- [Byzantine-Robust Decentralized Federated Learning](https://mlsanity.com/paper/2406.10416/) (2024)
- [Gradient Leakage Attack Resilient Deep Learning](https://mlsanity.com/paper/2112.13178/) (2021)
- [A Survey of Published Attacks on Intel SGX](https://mlsanity.com/paper/2006.13598/) (2020)
- [Privacy-Preserving Average Consensus via State Decomposition](https://mlsanity.com/paper/1902.09576/) (2019)
- [Multi-Agent Consensus Subject to Communication and Privacy Constraints](https://mlsanity.com/paper/2102.10642/) (2021)
- [State-Secrecy Codes for Networked Linear Systems](https://mlsanity.com/paper/1709.04530/) (2017)
- [Distortion based Light-weight Security for Cyber-Physical Systems](https://mlsanity.com/paper/2006.15998/) (2020)
- [Ensuring System-Level Protection against Eavesdropping Adversaries in Distributed Dynamical Systems](https://mlsanity.com/paper/2409.09539/) (2024)
- [Federated Learning Nodes Can Reconstruct Peers' Image Data](https://mlsanity.com/paper/2410.04661/) (2024)

## Built on by (most cited first, 2 of 2)

- [ModShift: Model Privacy via Designed Shifts](https://mlsanity.com/paper/2507.20060/) (2025)
- [MaxModShift: Model Privacy via Designed Shifts](https://mlsanity.com/paper/2608.09328/) (2026)

## Abstract (arXiv)

In this study, we investigate the protection offered by federated learning algorithms against eavesdropping adversaries. In our model, the adversary is capable of intercepting model updates transmitted from clients to the server, enabling it to create its own estimate of the model. Unlike previous research, which predominantly focuses on safeguarding client data, our work shifts attention protecting the client model itself. Through a theoretical analysis, we examine how various factors, such as the probability of client selection, the structure of local objective functions, global aggregation at the server, and the eavesdropper's capabilities, impact the overall level of protection. We further validate our findings through numerical experiments, assessing the protection by evaluating the model accuracy achieved by the adversary. Finally, we compare our results with methods based on differential privacy, underscoring their limitations in this specific context.