mlsanityData to 14 Oct 2026

FACT or Fiction: Can Truthful Mechanisms Eliminate Federated Free Riding?

arXiv 2405.13879 ↗First posted 22 May 2024cs.GT cs.DC cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Standard federated learning (FL) approaches are vulnerable to the free-rider dilemma: participating agents can contribute little to nothing yet receive a well-trained aggregated model. While prior mechanisms attempt to solve the free-rider dilemma, none have addressed the issue of truthfulness. In practice, adversarial agents can provide false information to the server in order to cheat its way out of contributing to federated training. In an effort to make free-riding-averse federated mechanisms truthful, and consequently less prone to breaking down in practice, we propose FACT. FACT is the first federated mechanism that: (1) eliminates federated free riding by using a penalty system, (2) ensures agents provide truthful information by creating a competitive environment, and (3) encourages agent participation by offering better performance than training alone. Empirically, FACT avoids free-riding when agents are untruthful, and reduces agent loss by over 4x.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 19 of its 44 references that are in the map. First posted on arXiv 22 May 2024.

Builds on

19 of 44 references.

References · 19

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2017Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descentcited by 502
  3. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
  4. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 462
  5. 2022FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correctioncited by 181
  6. 2020Collaborative Fairness in Federated Learningcited by 95
  7. 2020Byzantine-Resilient Secure Federated Learningcited by 93
  8. 2020Collaborative Machine Learning with Incentive-Aware Model Rewardscited by 71
  9. 2020Data Poisoning Attacks on Federated Machine Learningcited by 62
  10. 2020Poisoning Attacks on Algorithmic Fairnesscited by 59
  11. 2020Free-rider Attacks on Model Aggregation in Federated Learningcited by 57
  12. 2024Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Modelscited by 50
7 more
  1. 2019Free-riders in Federated Learning: Attacks and Defensescited by 49
  2. 2021Incentive Mechanisms for Federated Learning: From Economic and Game Theoretic Perspectivecited by 47
  3. 2020A Reputation Mechanism Is All You Need: Collaborative Fairness and Adversarial Robustness in Federated Learningcited by 41
  4. 2021One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learningcited by 39
  5. 2022Mechanisms that Incentivize Data Sharing in Federated Learningcited by 39
  6. 2021A Contract Theory based Incentive Mechanism for Federated Learningcited by 13
  7. 2024Fake or Compromised? Making Sense of Malicious Clients in Federated Learningcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025Incentivize Contribution and Learn Parameters Too: Federated Learning with Strategic Data Ownerscited by 1
  2. 2025MURIM: Multidimensional Reputation-based Incentive Mechanism for Federated Learningcited by 0
  3. 2026Incentive-Aware Federated Averaging with Performance Guarantees under Strategic Participationcited by 0