mlsanityData to 7 Oct 2026

Federated Learning with Unreliable Clients: Performance Analysis and Mechanism Design

arXiv 2105.06256 ↗First posted 10 May 2021cs.LG cs.DCcited by 9

Not on the map. Why?

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.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 25 of its 40 references that are in the map. First posted on arXiv 10 May 2021.

Builds on

25 of 40 references.

References · 25

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  3. 2018Federated Learning with Non-IID Datacited by 1,099
  4. 2018How To Backdoor Federated Learningcited by 745
  5. 2018Local SGD Converges Fast and Communicates Littlecited by 595
  6. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 528
  7. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
  8. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 479
  9. 2018Adaptive Federated Learning in Resource Constrained Edge Computing Systemscited by 408
  10. 2018Analyzing Federated Learning through an Adversarial Lenscited by 346
  11. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 326
  12. 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 285
13 more
  1. 2018Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learningcited by 242
  2. 2017On the convergence properties of a K-step averaging stochastic gradient descent algorithm for nonconvex optimizationcited by 91
  3. 2019Byzantine-Robust Federated Machine Learning through Adaptive Model Averagingcited by 70
  4. 2020Deep Anomaly Detection for Time-series Data in Industrial IoT: A Communication-Efficient On-device Federated Learning Approachcited by 56
  5. 2019On Safeguarding Privacy and Security in the Framework of Federated Learningcited by 55
  6. 2019Attack-Resistant Federated Learning with Residual-based Reweightingcited by 40
  7. 2017Security Evaluation of Pattern Classifiers under Attackcited by 39
  8. 2018No Peek: A Survey of private distributed deep learningcited by 30
  9. 2019Shielding Collaborative Learning: Mitigating Poisoning Attacks through Client-Side Detectioncited by 25
  10. 2018Distributed Anomaly Detection using Autoencoder Neural Networks in WSN for IoTcited by 16
  11. 2020Enabling AI in Future Wireless Networks: A Data Life Cycle Perspectivecited by 14
  12. 2018Privacy Preservation in Location-Based Services: A Novel Metric and Attack Modelcited by 5
  13. 2019Privacy Preserving Location Data Publishing: A Machine Learning Approachcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 3; 2023: 1; 2024: 1; 2025: 2; 2026: 1.

9 papers.

  1. 2021Federated Learning for Intrusion Detection System: Concepts, Challenges and Future Directionscited by 22
  2. 2022Long-Short History of Gradients is All You Need: Detecting Malicious and Unreliable Clients in Federated Learningcited by 7
  3. 2025FNBench: Benchmarking Robust Federated Learning against Noisy Labelscited by 6
  4. 2022Multi-trainer Interactive Reinforcement Learning Systemcited by 2
  5. 2023Mobility-Aware Joint User Scheduling and Resource Allocation for Low Latency Federated Learningcited by 2
  6. 2025ASMR: Angular Support for Malfunctioning Client Resilience in Federated Learningcited by 1
  7. 2022Mitigating Data Absence in Federated Learning Using Privacy-Controllable Data Digestscited by 0
  8. 2024FedMap: Iterative Magnitude-Based Pruning for Communication-Efficient Federated Learningcited by 0
  9. 2026Robust Server Defense Against Unreliable Clients in One-Shot Fair Collaborative Machine Learningcited by 0