mlsanityData to 14 Oct 2026

ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning

arXiv 2509.09534 ↗First posted 11 Sep 2025cs.LG cs.DCcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) emerged as a widely studied paradigm for distributed learning. Despite its many advantages, FL remains vulnerable to adversarial attacks, especially under data heterogeneity. We propose a new Byzantine-robust FL algorithm called ProDiGy. The key novelty lies in evaluating the client gradients using a joint dual scoring system based on the gradients' proximity and dissimilarity. We demonstrate through extensive numerical experiments that ProDiGy outperforms existing defenses in various scenarios. In particular, when the clients' data do not follow an IID distribution, while other defense mechanisms fail, ProDiGy maintains strong defense capabilities and model accuracy. These findings highlight the effectiveness of a dual perspective approach that promotes natural similarity among honest clients while detecting suspicious uniformity as a potential indicator of an attack.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 24 of its 37 references that are in the map. First posted on arXiv 11 Sep 2025.

Builds on

24 of 37 references.

References · 24

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019Advances and Open Problems in Federated Learningcited by 3,046
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  4. 2018LEAF: A Benchmark for Federated Settingscited by 792
  5. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 711
  6. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 682
  7. 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 346
  8. 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 329
  9. 2019Robust Aggregation for Federated Learningcited by 317
  10. 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 288
  11. 2018Mitigating Sybils in Federated Learning Poisoningcited by 161
  12. 2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 161
12 more
  1. 2019Fall of Empires: Breaking Byzantine-tolerant SGD by Inner Product Manipulationcited by 141
  2. 2020Learning from History for Byzantine Robust Optimizationcited by 137
  3. 2020Byzantine-Robust Learning on Heterogeneous Datasets via Bucketingcited by 128
  4. 2022Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challengescited by 84
  5. 2023Fixing by Mixing: A Recipe for Optimal Byzantine ML under Heterogeneitycited by 65
  6. 2017Distributed Statistical Machine Learning in Adversarial Settings: Byzantine Gradient Descentcited by 59
  7. 2020Byzantine-Resilient Non-Convex Stochastic Gradient Descentcited by 57
  8. 2021Challenges and Approaches for Mitigating Byzantine Attacks in Federated Learningcited by 47
  9. 2023An Experimental Study of Byzantine-Robust Aggregation Schemes in Federated Learningcited by 32
  10. 2023FedGT: Identification of Malicious Clients in Federated Learning with Secure Aggregationcited by 16
  11. 2024Adaptive Gradient Clipping for Robust Federated Learningcited by 11
  12. 2021Byzantine-robust Federated Learning through Spatial-temporal Analysis of Local Model Updatescited by 8

Built on by

Not cited yet.