Robust Reputation-Driven Crowdsourced Federated Learning
Mouhamed Amine Bouchiha, Gregory Blanc
cs.LG, cs.CR, cs.DC
Submitted: 2026-08-11
Updated: 2026-08-12
Comments: Accepted for presentation at the HotDiSec Workshop, co-located with ESORICS'26
Code: https://github.com/mohaminemed/R2CFL
License: http://creativecommons.org/licenses/by/4.0/
The gist: Crowdsourced Federated Learning (CrowdFL) extends traditional federated learning by enabling open and heterogeneous participation through a crowdsourcing paradigm.
Terminology
Abstract
Crowdsourced Federated Learning (CrowdFL) extends traditional federated learning by enabling open and heterogeneous participation through a crowdsourcing paradigm. In this setting, reputation-driven incentive mechanisms are commonly employed to guide worker selection and enhance trustworthiness. While such approaches improve participant reliability, existing frameworks largely overlook the quantification of their robustness against stealthy adversaries, particularly those capable of evading standard detection mechanisms. To fill this gap, this paper proposes R2CFL, a robust reputation-driven CrowdFL framework. R2CFL introduces a robust reputation model coupled with a nearest neighbor mixing (R2-NNM) defense mechanism that links reputation evolution with the filtering of updates during aggregation. The proposed mechanism prevents stealthy attackers from gradually accumulating trust and influencing future tasks. Experimental results demonstrate that R2-NNM matches or surpasses state-of-the-art Byzantine-robust and backdoor defense mechanisms against adaptive attackers. Furthermore, when integrated with existing detect-and-filter defenses, the proposed reputation model faithfully captures the statistical robustness of the underlying defense by producing reputation scores that closely reflect its true positive and false positive characteristics.
Sources
- LLMChain: Blockchain-based Reputation System for Sharing and Evaluating Large Language Models
- SettleFL: Trustless and Scalable Reward Settlement Protocol for Federated Learning on Permissionless Blockchains (Extended version)
- DeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model Inspection
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks