Analyzing the Impact of Partial Sharing on the Resilience of Online Federated Learning Against Model Poisoning Attacks

Ehsan Lari, Vinay Chakravarthi Gogineni, Reza Arablouei, Stefan Werner

Abstract

Federated Learning (FL) enables decentralized model training but remains vulnerable to Byzantine attacks, where malicious clients submit "poisoned" updates. This study explores Partial-Sharing Online Federated Learning (PSO-Fed) as a robust alternative. Originally designed for communication efficiency, partial sharing is shown to inherently dilute the impact of malicious updates. We provide a theoretical analysis of the Mean Square Error (MSE) under attack and demonstrate through simulations that PSO-Fed significantly outperforms existing robust aggregation techniques.

Introduction

The decentralized nature of Federated Learning creates a significant security vulnerability: Byzantine attacks. In these scenarios, malicious actors can steer the global model toward failure by injecting noise or biased updates. While robust aggregation methods like median-based filtering exist, they often impose high computational costs on resource-constrained IoT devices. This research, recently published in IEEE Transactions on Signal and Information Processing over Networks, investigates whether communication-efficient strategies, specifically partial sharing, can provide "out-of-the-box" resilience against such model-poisoning attacks.

Methodology: PSO-Fed

The proposed framework, Partial-Sharing Online Federated Learning (PSO-Fed), combines two key strategies:

  1. Partial Sharing: Instead of transmitting the full vector of $D$ model parameters, each client shares only a subset $M$ ($M < D$) per iteration.
  2. Online Learning: The model is updated continuously as new data streams arrive, ensuring the global model adapts to real-time changes.

The study models Byzantine clients as adversaries that inject zero-mean white Gaussian noise into their shared updates with a specific attack probability ($p_a$). By using block Kronecker products and vectorization, the authors derived a theoretical steady-state MSE, allowing for precise performance prediction based on network parameters and attack intensity.

Key Insights and Results

Sparsity as a Natural Defense

A primary finding is that partial sharing acts as a physical filter. By restricting the number of parameters shared by any single client, the "poison" introduced by a Byzantine actor is prevented from affecting the entire global model simultaneously. This "dilution" effect allows the network to maintain convergence even when a significant portion of the clients are compromised.

Steady-state test MSE vs. number of Byzantine clients for various FL algorithms.

As shown in Figure 1, PSO-Fed maintains a significantly lower steady-state MSE compared to standard Online-Fed and other state-of-the-art (SOTA) methods like SignSGD, CS-Fed, and QS-Fed as the number of Byzantine clients increases. In a 100-client network, PSO-Fed can maintain a 5-10 dB advantage over its competitors.

The Non-Trivial Optimal Stepsize

In standard stochastic gradient descent (SGD), a smaller stepsize ($\mu$) typically leads to lower steady-state error. However, this research reveals a critical shift under adversarial conditions: there exists a non-zero optimal stepsize ($\mu^*$).

Network-wide average MSE vs. stepsize $\mu$, highlighting the optimal stepsize $\mu^*$ under attack.

Figure 6 illustrates this phenomenon. If the stepsize is too small, the model becomes overly sensitive to the persistent noise from attackers; if it is too large, the system becomes unstable. Identifying this "sweet spot" is essential for maximizing the robustness of FL systems in hostile environments. Furthermore, the inclusion of a Stochastic Selection Algorithm (SSA) further enhances performance across various stepsize regimes.

Conclusion

PSO-Fed proves to be a dual-purpose solution, offering both communication efficiency and robust defense against model poisoning. The theoretical framework developed in this paper matches simulation results with high accuracy, providing a reliable tool for system designers. Future work will extend these findings to non-convex deep learning models and investigate resilience against more sophisticated, targeted backdoor attacks.

Summary updated

BibTeX
@article{lari2025analyzing,
  author = {Ehsan Lari and Vinay Chakravarthi Gogineni and Reza Arablouei and Stefan Werner},
  title = {{Analyzing the Impact of Partial Sharing on the Resilience of Online Federated Learning Against Model Poisoning Attacks}},
  journal = {IEEE Trans. Signal Inf. Process. Over Networks},
  year = {2025},
  doi = {10.1109/tsipn.2025.3559444},
}
Figure