mlsanityData to 7 Oct 2026

Can Decentralized Learning be more robust than Federated Learning?

arXiv 2303.03829 ↗First posted 7 Mar 2023cs.LG cs.CRcited by 6

Not on the map. Why?

Abstract (arXiv)

Decentralized Learning (DL) is a peer--to--peer learning approach that allows a group of users to jointly train a machine learning model. To ensure correctness, DL should be robust, i.e., Byzantine users must not be able to tamper with the result of the collaboration. In this paper, we introduce two textitnew attacks against DL where a Byzantine user can: make the network converge to an arbitrary model of their choice, and exclude an arbitrary user from the learning process. We demonstrate our attacks' efficiency against Self--Centered Clipping, the state--of--the--art robust DL protocol. Finally, we show that the capabilities decentralization grants to Byzantine users result in decentralized learning always providing less robustness than federated learning.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 20 of its 35 references that are in the map. First posted on arXiv 7 Mar 2023.

Builds on

20 of 35 references.

References · 20

  1. 2018How To Backdoor Federated Learningcited by 745
  2. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
  3. 2017Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descentcited by 496
  4. 2018Analyzing Federated Learning through an Adversarial Lenscited by 346
  5. 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 324
  6. 2019Robust Aggregation for Federated Learningcited by 314
  7. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 307
  8. 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 285
  9. 2020Learning from History for Byzantine Robust Optimizationcited by 137
  10. 2019Fall of Empires: Breaking Byzantine-tolerant SGD by Inner Product Manipulationcited by 136
  11. 2021Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learningcited by 116
  12. 2021Eluding Secure Aggregation in Federated Learning via Model Inconsistencycited by 66
8 more
  1. 2020Data Poisoning Attacks on Federated Machine Learningcited by 58
  2. 2020Collaborative Learning in the Jungle (Decentralized, Byzantine, Heterogeneous, Asynchronous and Nonconvex Learning)cited by 54
  3. 2019BRIDGE: Byzantine-resilient Decentralized Gradient Descentcited by 45
  4. 2018Defending Against Saddle Point Attack in Byzantine-Robust Distributed Learningcited by 32
  5. 2022Byzantines can also Learn from History: Fall of Centered Clipping in Federated Learningcited by 8
  6. 2021Robust and Privacy-Preserving Collaborative Learning: A Comprehensive Surveycited by 5
  7. 2022Security Analysis of SplitFed Learningcited by 5
  8. 2022Network-Level Adversaries in Federated Learningcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 0; 2026: 3.

6 papers.

  1. 2024Privacy-Preserving Aggregation for Decentralized Learning with Byzantine-Robustnesscited by 4
  2. 2023The Impact of Adversarial Node Placement in Decentralized Federated Learning Networkscited by 1
  3. 2024Aggressive or Imperceptible, or Both: Network Pruning Assisted Hybrid Byzantines in Federated Learningcited by 0
  4. 2026On Gossip Algorithms for Machine Learning with Pairwise Objectivescited by 0
  5. 2026Optimizing Byzantine Node Placement in Decentralized Federated Learningcited by 0
  6. 2026Robust Decentralized Personalized Federated Learning via Prediction-Constrained Neighborhood Collaborationcited by 0