mlsanityData to 14 Oct 2026

RobustFSM: Submodular Maximization in Federated Setting with Malicious Clients

arXiv 2511.02029 ↗First posted 3 Nov 2025cs.LG cs.AI cs.DCcited by 0

Not on the map. Why?

Abstract (arXiv)

Submodular maximization is an optimization problem benefiting many machine learning applications, where we seek a small subset best representing an extremely large dataset. We focus on the federated setting where the data are locally owned by decentralized clients who have their own definitions for the quality of representability. This setting requires repetitive aggregation of local information computed by the clients. While the main motivation is to respect the privacy and autonomy of the clients, the federated setting is vulnerable to client misbehaviors: malicious clients might share fake information. An analogy is backdoor attack in conventional federated learning, but our challenge differs freshly due to the unique characteristics of submodular maximization. We propose RobustFSM, a federated submodular maximization solution that is robust to various practical client attacks. Its performance is substantiated with an empirical evaluation study using real-world datasets. Numerical results show that the solution quality of RobustFSM substantially exceeds that of the conventional federated algorithm when attacks are severe. The degree of this improvement depends on the dataset and attack scenarios, which can be as high as 200%

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 12 of its 35 references that are in the map. First posted on arXiv 3 Nov 2025.

Builds on

12 of 35 references.

References · 12

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2021MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classificationcited by 690
  4. 2019Robust Aggregation for Federated Learningcited by 317
  5. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 309
  6. 2022FLDetector: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clientscited by 125
  7. 2021CRFL: Certifiably Robust Federated Learning against Backdoor Attackscited by 91
  8. 2017Distributed Statistical Machine Learning in Adversarial Settings: Byzantine Gradient Descentcited by 59
  9. 2023Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directionscited by 33
  10. 2023BayBFed: Bayesian Backdoor Defense for Federated Learningcited by 23
  11. 2024FedBlock: A Blockchain Approach to Federated Learning against Backdoor Attackscited by 2
  12. 2024Decomposable Submodular Maximization in Federated Settingcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025FedGuard: A Diverse-Byzantine-Robust Mechanism for Federated Learning with Major Malicious Clients ↗
  2. 2024Byzantine-Robust Federated Learning: An Overview With Focus on Developing Sybil-based Attacks to Backdoor Augmented Secure Aggregation Protocols
  3. 2026FAROS: Robust Federated Learning with Adaptive Scaling against Backdoor Attacks
  4. 2025AdRo-FL: Informed and Secure Client Selection for Federated Learning in the Presence of Adversarial Aggregator
  5. 2023A Survey on Vulnerability of Federated Learning: A Learning Algorithm Perspective
  6. 2023Adversarial Robustness Unhardening via Backdoor Attacks in Federated Learning
  7. 2026Mitigating Backdoor Attacks in Federated Learning Using PPA and MiniMax Game Theory
  8. 2022FedCC: Robust Federated Learning against Model Poisoning Attacks