mlsanityData to 14 Oct 2026

Detect & Score: Privacy-Preserving Misbehaviour Detection and Contribution Evaluation in Federated Learning

arXiv 2506.23583 ↗First posted 30 Jun 2025cs.CR cs.DC cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Federated learning with secure aggregation enables private and collaborative learning from decentralised data without leaking sensitive client information. However, secure aggregation also complicates the detection of malicious client behaviour and the evaluation of individual client contributions to the learning. To address these challenges, QI (Pejo et al.) and FedGT (Xhemrishi et al.) were proposed for contribution evaluation (CE) and misbehaviour detection (MD), respectively. QI, however, lacks adequate MD accuracy due to its reliance on the random selection of clients in each training round, while FedGT lacks the CE ability. In this work, we combine the strengths of QI and FedGT to achieve both robust MD and accurate CE. Our experiments demonstrate superior performance compared to using either method independently.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 32 of its 48 references that are in the map. First posted on arXiv 30 Jun 2025.

Builds on

32 of 48 references.

References · 32

  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. 2019Deep Leakage from Gradientscited by 1,021
  4. 2018How To Backdoor Federated Learningcited by 765
  5. 2016Stealing Machine Learning Models via Prediction APIscited by 619
  6. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 520
  7. 2020Backdoor Learning: A Surveycited by 426
  8. 2019Robust Aggregation for Federated Learningcited by 317
  9. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 275
  10. 2018Mitigating Sybils in Federated Learning Poisoningcited by 161
  11. 2017A Survey on Homomorphic Encryption Schemes: Theory and Implementationcited by 156
  12. 2020A Principled Approach to Data Valuation for Federated Learningcited by 127
20 more
  1. 2022FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settingscited by 125
  2. 2022The Shapley Value in Machine Learningcited by 98
  3. 2020Byzantine-Resilient Secure Federated Learningcited by 93
  4. 2019Measure Contribution of Participants in Federated Learningcited by 79
  5. 2020Fast-Convergent Federated Learning with Adaptive Weightingcited by 67
  6. 2023OpenDataVal: a Unified Benchmark for Data Valuationcited by 55
  7. 2022Autoregressive Perturbations for Data Poisoningcited by 46
  8. 2021Leave-one-out Unfairnesscited by 36
  9. 2019SoK: Differential Privaciescited by 34
  10. 2022Learning to Invert: Simple Adaptive Attacks for Gradient Inversion in Federated Learningcited by 30
  11. 2023Label Poisoning is All You Needcited by 29
  12. 2021Rational Shapley Valuescited by 18
  13. 2021Transparent Contribution Evaluation for Secure Federated Learning on Blockchaincited by 16
  14. 2023FedGT: Identification of Malicious Clients in Federated Learning with Secure Aggregationcited by 16
  15. 2020Quality Inference in Federated Learning with Secure Aggregationcited by 15
  16. 2020An Exploratory Analysis on Users' Contributions in Federated Learningcited by 15
  17. 2022Secure Shapley Value for Cross-Silo Federated Learning (Technical Report)cited by 13
  18. 2022Differentially Private Shapley Values for Data Evaluationcited by 8
  19. 2025FedSV: Byzantine-Robust Federated Learning via Shapley Valuecited by 6
  20. 2022Defense Strategies Toward Model Poisoning Attacks in Federated Learning: A Surveycited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Private and Robust Contribution Evaluation in Federated Learningcited by 1