DMPA: Model Poisoning Attacks on Decentralized Federated Learning for Model Differences

TL;DR

This paper introduces DMPA, a novel model poisoning attack on decentralized federated learning, demonstrating its effectiveness and superiority over existing methods through extensive validation.

Contribution

It proposes DMPA, a new collusive poisoning attack leveraging differential analysis of malicious models, filling a research gap in decentralized FL security.

Findings

DMPA outperforms existing poisoning strategies in multiple datasets.

The attack effectively reduces model performance in decentralized FL.

Validation confirms the attack's robustness and efficiency.

Abstract

Federated learning (FL) has garnered significant attention as a prominent privacy-preserving Machine Learning (ML) paradigm. Decentralized FL (DFL) eschews traditional FL's centralized server architecture, enhancing the system's robustness and scalability. However, these advantages of DFL also create new vulnerabilities for malicious participants to execute adversarial attacks, especially model poisoning attacks. In model poisoning attacks, malicious participants aim to diminish the performance of benign models by creating and disseminating the compromised model. Existing research on model poisoning attacks has predominantly concentrated on undermining global models within the Centralized FL (CFL) paradigm, while there needs to be more research in DFL. To fill the research gap, this paper proposes an innovative model poisoning attack called DMPA. This attack calculates the differential characteristics of multiple malicious client models and obtains the most effective poisoning strategy, thereby orchestrating a collusive attack by multiple participants. The effectiveness of this attack is validated across multiple datasets, with results indicating that the DMPA approach consistently surpasses existing state-of-the-art FL model poisoning attack strategies.