# Federated Learning with Unreliable Clients: Performance Analysis and Mechanism Design

arXiv: https://arxiv.org/abs/2105.06256 · HTML: https://mlsanity.com/paper/2105.06256/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 40 references that are in the map.
- First posted on arXiv 10 May 2021.

## Builds on (most cited first, 25 of 25)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [Federated Learning with Non-IID Data](https://mlsanity.com/paper/1806.00582/) (2018)
- [How To Backdoor Federated Learning](https://mlsanity.com/paper/1807.00459/) (2018)
- [Local SGD Converges Fast and Communicates Little](https://mlsanity.com/paper/1805.09767/) (2018)
- [Federated Learning with Differential Privacy: Algorithms and Performance Analysis](https://mlsanity.com/paper/1911.00222/) (2019)
- [Exploiting Unintended Feature Leakage in Collaborative Learning](https://mlsanity.com/paper/1805.04049/) (2018)
- [Local Model Poisoning Attacks to Byzantine-Robust Federated Learning](https://mlsanity.com/paper/1911.11815/) (2019)
- [Adaptive Federated Learning in Resource Constrained Edge Computing Systems](https://mlsanity.com/paper/1804.05271/) (2018)
- [Analyzing Federated Learning through an Adversarial Lens](https://mlsanity.com/paper/1811.12470/) (2018)
- [Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning](https://mlsanity.com/paper/1702.07464/) (2017)
- [A Little Is Enough: Circumventing Defenses For Distributed Learning](https://mlsanity.com/paper/1902.06156/) (2019)
- [Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning](https://mlsanity.com/paper/1812.00535/) (2018)
- [On the convergence properties of a K-step averaging stochastic gradient descent algorithm for nonconvex optimization](https://mlsanity.com/paper/1708.01012/) (2017)
- [Byzantine-Robust Federated Machine Learning through Adaptive Model Averaging](https://mlsanity.com/paper/1909.05125/) (2019)
- [Deep Anomaly Detection for Time-series Data in Industrial IoT: A Communication-Efficient On-device Federated Learning Approach](https://mlsanity.com/paper/2007.09712/) (2020)
- [On Safeguarding Privacy and Security in the Framework of Federated Learning](https://mlsanity.com/paper/1909.06512/) (2019)
- [Attack-Resistant Federated Learning with Residual-based Reweighting](https://mlsanity.com/paper/1912.11464/) (2019)
- [Security Evaluation of Pattern Classifiers under Attack](https://mlsanity.com/paper/1709.00609/) (2017)
- [No Peek: A Survey of private distributed deep learning](https://mlsanity.com/paper/1812.03288/) (2018)
- [Shielding Collaborative Learning: Mitigating Poisoning Attacks through Client-Side Detection](https://mlsanity.com/paper/1910.13111/) (2019)
- [Distributed Anomaly Detection using Autoencoder Neural Networks in WSN for IoT](https://mlsanity.com/paper/1812.04872/) (2018)
- [Enabling AI in Future Wireless Networks: A Data Life Cycle Perspective](https://mlsanity.com/paper/2003.00866/) (2020)
- [Privacy Preservation in Location-Based Services: A Novel Metric and Attack Model](https://mlsanity.com/paper/1805.06104/) (2018)
- [Privacy Preserving Location Data Publishing: A Machine Learning Approach](https://mlsanity.com/paper/1902.08934/) (2019)

## Built on by (most cited first, 9 of 9)

- [Federated Learning for Intrusion Detection System: Concepts, Challenges and Future Directions](https://mlsanity.com/paper/2106.09527/) (2021)
- [Long-Short History of Gradients is All You Need: Detecting Malicious and Unreliable Clients in Federated Learning](https://mlsanity.com/paper/2208.10273/) (2022)
- [FNBench: Benchmarking Robust Federated Learning against Noisy Labels](https://mlsanity.com/paper/2505.06684/) (2025)
- [Mobility-Aware Joint User Scheduling and Resource Allocation for Low Latency Federated Learning](https://mlsanity.com/paper/2307.09263/) (2023)
- [Multi-trainer Interactive Reinforcement Learning System](https://mlsanity.com/paper/2210.08050/) (2022)
- [ASMR: Angular Support for Malfunctioning Client Resilience in Federated Learning](https://mlsanity.com/paper/2508.02414/) (2025)
- [Mitigating Data Absence in Federated Learning Using Privacy-Controllable Data Digests](https://mlsanity.com/paper/2210.00737/) (2022)
- [FedMap: Iterative Magnitude-Based Pruning for Communication-Efficient Federated Learning](https://mlsanity.com/paper/2406.19050/) (2024)
- [Robust Server Defense Against Unreliable Clients in One-Shot Fair Collaborative Machine Learning](https://mlsanity.com/paper/2605.08616/) (2026)

## Abstract (arXiv)

Owing to the low communication costs and privacy-promoting capabilities, Federated Learning (FL) has become a promising tool for training effective machine learning models among distributed clients. However, with the distributed architecture, low quality models could be uploaded to the aggregator server by unreliable clients, leading to a degradation or even a collapse of training. In this paper, we model these unreliable behaviors of clients and propose a defensive mechanism to mitigate such a security risk. Specifically, we first investigate the impact on the models caused by unreliable clients by deriving a convergence upper bound on the loss function based on the gradient descent updates. Our theoretical bounds reveal that with a fixed amount of total computational resources, there exists an optimal number of local training iterations in terms of convergence performance. We further design a novel defensive mechanism, named deep neural network based secure aggregation (DeepSA). Our experimental results validate our theoretical analysis. In addition, the effectiveness of DeepSA is verified by comparing with other state-of-the-art defensive mechanisms.