mlsanityData to 7 Oct 2026

ACE: A Model Poisoning Attack on Contribution Evaluation Methods in Federated Learning

arXiv 2405.20975 ↗First posted 31 May 2024cs.CR cs.AI cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

In Federated Learning (FL), a set of clients collaboratively train a machine learning model (called global model) without sharing their local training data. The local training data of clients is typically non-i.i.d. and heterogeneous, resulting in varying contributions from individual clients to the final performance of the global model. In response, many contribution evaluation methods were proposed, where the server could evaluate the contribution made by each client and incentivize the high-contributing clients to sustain their long-term participation in FL. Existing studies mainly focus on developing new metrics or algorithms to better measure the contribution of each client. However, the security of contribution evaluation methods of FL operating in adversarial environments is largely unexplored. In this paper, we propose the first model poisoning attack on contribution evaluation methods in FL, termed ACE. Specifically, we show that any malicious client utilizing ACE could manipulate the parameters of its local model such that it is evaluated to have a high contribution by the server, even when its local training data is indeed of low quality. We perform both theoretical analysis and empirical evaluations of ACE. Theoretically, we show our design of ACE can effectively boost the malicious client's perceived contribution when the server employs the widely-used cosine distance metric to measure contribution. Empirically, our results show ACE effectively and efficiently deceive five state-of-the-art contribution evaluation methods. In addition, ACE preserves the accuracy of the final global models on testing inputs. We also explore six countermeasures to defend ACE. Our results show they are inadequate to thwart ACE, highlighting the urgent need for new defenses to safeguard the contribution evaluation methods in FL.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 51 of its 89 references that are in the map. First posted on arXiv 31 May 2024.

Builds on

51 of 89 references.

References · 51

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  4. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,479
  5. 2018Federated Learning with Non-IID Datacited by 1,099
  6. 2018How To Backdoor Federated Learningcited by 745
  7. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
  8. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 479
  9. 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 349
  10. 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 330
  11. 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 324
  12. 2019Robust Aggregation for Federated Learningcited by 314
38 more
  1. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 307
  2. 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 285
  3. 2019Towards Efficient Data Valuation Based on the Shapley Valuecited by 279
  4. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 266
  5. 2019Can You Really Backdoor Federated Learning?cited by 250
  6. 2021Federated Learning for Internet of Things: A Comprehensive Surveycited by 247
  7. 2018Mitigating Sybils in Federated Learning Poisoningcited by 158
  8. 2021Federated Learning for Open Bankingcited by 138
  9. 2019Fall of Empires: Breaking Byzantine-tolerant SGD by Inner Product Manipulationcited by 136
  10. 2020A Principled Approach to Data Valuation for Federated Learningcited by 127
  11. 2020Byzantine-Robust Learning on Heterogeneous Datasets via Bucketingcited by 125
  12. 2022FLDetector: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clientscited by 119
  13. 2022Neurotoxin: Durable Backdoors in Federated Learningcited by 97
  14. 2020Collaborative Fairness in Federated Learningcited by 95
  15. 2018Generalized Byzantine-tolerant SGDcited by 94
  16. 2020Defending against Backdoors in Federated Learning with Robust Learning Ratecited by 82
  17. 2019Measure Contribution of Participants in Federated Learningcited by 78
  18. 2022DeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model Inspectioncited by 78
  19. 2021GTG-Shapley: Efficient and Accurate Participant Contribution Evaluation in Federated Learningcited by 73
  20. 2019Byzantine-Robust Federated Machine Learning through Adaptive Model Averagingcited by 70
  21. 2022MPAF: Model Poisoning Attacks to Federated Learning based on Fake Clientscited by 65
  22. 2021Towards Fairness-Aware Federated Learningcited by 57
  23. 2022FedRecover: Recovering from Poisoning Attacks in Federated Learning using Historical Informationcited by 53
  24. 2023Fair Federated Medical Image Segmentation via Client Contribution Estimationcited by 50
  25. 2019Free-riders in Federated Learning: Attacks and Defensescited by 48
  26. 2020FMore: An Incentive Scheme of Multi-dimensional Auction for Federated Learning in MECcited by 48
  27. 2021Challenges and Approaches for Mitigating Byzantine Attacks in Federated Learningcited by 46
  28. 2019Abnormal Client Behavior Detection in Federated Learningcited by 39
  29. 2020Mitigating Backdoor Attacks in Federated Learningcited by 39
  30. 2020A Reputation Mechanism Is All You Need: Collaborative Fairness and Adversarial Robustness in Federated Learningcited by 38
  31. 2020FOCUS: Dealing with Label Quality Disparity in Federated Learningcited by 36
  32. 2022AFLGuard: Byzantine-robust Asynchronous Federated Learningcited by 29
  33. 2023BayBFed: Bayesian Backdoor Defense for Federated Learningcited by 23
  34. 2021Improving Fairness for Data Valuation in Horizontal Federated Learningcited by 22
  35. 2022Fair and efficient contribution valuation for vertical federated learningcited by 18
  36. 2021FedSAE: A Novel Self-Adaptive Federated Learning Framework in Heterogeneous Systemscited by 16
  37. 2022Secure Shapley Value for Cross-Silo Federated Learning (Technical Report)cited by 13
  38. 2023A Survey of Federated Evaluation in Federated Learningcited by 7

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

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

5 papers.

  1. 2025Vertical Federated Learning in Practice: The Good, the Bad, and the Uglycited by 4
  2. 2025On the Fragility of Contribution Score Computation in Federated Learningcited by 1
  3. 2024FRIDA: Free-Rider Detection using Privacy Attackscited by 0
  4. 2025Trustless Federated Learning at Edge-Scale: A Compositional Architecture for Decentralized, Verifiable, and Incentive-Aligned Coordinationcited by 0
  5. 2026Beyond performance-wise Contribution Evaluation in Federated Learningcited by 0