FedQV: Leveraging Quadratic Voting in Federated Learning
This work addresses security issues in federated learning for collaborative model training, offering an incremental improvement over existing methods.
The paper tackles the vulnerability of federated learning to poisoning attacks by proposing FedQV, a novel aggregation algorithm based on quadratic voting, which theoretically ensures truthful bidding and empirically demonstrates superior performance against attacks on real-world datasets.
Federated Learning (FL) permits different parties to collaboratively train a global model without disclosing their respective local labels. A crucial step of FL, that of aggregating local models to produce the global one, shares many similarities with public decision-making, and elections in particular. In that context, a major weakness of FL, namely its vulnerability to poisoning attacks, can be interpreted as a consequence of the one person one vote (henceforth 1p1v) principle underpinning most contemporary aggregation rules. In this paper, we propose FedQV, a novel aggregation algorithm built upon the quadratic voting scheme, recently proposed as a better alternative to 1p1v-based elections. Our theoretical analysis establishes that FedQV is a truthful mechanism in which bidding according to one's true valuation is a dominant strategy that achieves a convergence rate that matches those of state-of-the-art methods. Furthermore, our empirical analysis using multiple real-world datasets validates the superior performance of FedQV against poisoning attacks. It also shows that combining FedQV with unequal voting ``budgets'' according to a reputation score increases its performance benefits even further. Finally, we show that FedQV can be easily combined with Byzantine-robust privacy-preserving mechanisms to enhance its robustness against both poisoning and privacy attacks.