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

arXiv: https://arxiv.org/abs/2405.13879 · HTML: https://mlsanity.com/paper/2405.13879/

## 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 (most cited first, 19 of 19)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent](https://mlsanity.com/paper/1705.09056/) (2017)
- [Local Model Poisoning Attacks to Byzantine-Robust Federated Learning](https://mlsanity.com/paper/1911.11815/) (2019)
- [Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models](https://mlsanity.com/paper/1712.04248/) (2017)
- [FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correction](https://mlsanity.com/paper/2203.11751/) (2022)
- [Collaborative Fairness in Federated Learning](https://mlsanity.com/paper/2008.12161/) (2020)
- [Byzantine-Resilient Secure Federated Learning](https://mlsanity.com/paper/2007.11115/) (2020)
- [Collaborative Machine Learning with Incentive-Aware Model Rewards](https://mlsanity.com/paper/2010.12797/) (2020)
- [Data Poisoning Attacks on Federated Machine Learning](https://mlsanity.com/paper/2004.10020/) (2020)
- [Poisoning Attacks on Algorithmic Fairness](https://mlsanity.com/paper/2004.07401/) (2020)
- [Free-rider Attacks on Model Aggregation in Federated Learning](https://mlsanity.com/paper/2006.11901/) (2020)
- [Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models](https://mlsanity.com/paper/2402.06659/) (2024)
- [Free-riders in Federated Learning: Attacks and Defenses](https://mlsanity.com/paper/1911.12560/) (2019)
- [Incentive Mechanisms for Federated Learning: From Economic and Game Theoretic Perspective](https://mlsanity.com/paper/2111.11850/) (2021)
- [A Reputation Mechanism Is All You Need: Collaborative Fairness and Adversarial Robustness in Federated Learning](https://mlsanity.com/paper/2011.10464/) (2020)
- [One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning](https://mlsanity.com/paper/2103.03228/) (2021)
- [Mechanisms that Incentivize Data Sharing in Federated Learning](https://mlsanity.com/paper/2207.04557/) (2022)
- [A Contract Theory based Incentive Mechanism for Federated Learning](https://mlsanity.com/paper/2108.05568/) (2021)
- [Fake or Compromised? Making Sense of Malicious Clients in Federated Learning](https://mlsanity.com/paper/2403.06319/) (2024)

## Built on by (most cited first, 3 of 3)

- [Incentivize Contribution and Learn Parameters Too: Federated Learning with Strategic Data Owners](https://mlsanity.com/paper/2505.12010/) (2025)
- [MURIM: Multidimensional Reputation-based Incentive Mechanism for Federated Learning](https://mlsanity.com/paper/2512.13955/) (2025)
- [Incentive-Aware Federated Averaging with Performance Guarantees under Strategic Participation](https://mlsanity.com/paper/2603.20873/) (2026)

## 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.