ADCA: Attention-Driven Multi-Party Collusion Attack in Federated Self-Supervised Learning

TL;DR

This paper introduces ADCA, a novel attention-driven collusion attack that exploits local trigger decomposition and coalition-based aggregation to effectively embed backdoors in federated self-supervised learning, overcoming previous limitations.

Contribution

The paper proposes a new collusion attack method using attention mechanisms and trigger decomposition, enhancing backdoor attack success and robustness in federated self-supervised learning.

Findings

ADCA achieves higher attack success rates than existing methods.

ADCA maintains backdoor effectiveness across heterogeneous client environments.

Experimental results confirm ADCA's robustness and superiority in multiple scenarios.

Abstract

Federated Self-Supervised Learning (FSSL) integrates the privacy advantages of distributed training with the capability of self-supervised learning to leverage unlabeled data, showing strong potential across applications. However, recent studies have shown that FSSL is also vulnerable to backdoor attacks. Existing attacks are limited by their trigger design, which typically employs a global, uniform trigger that is easily detected, gets diluted during aggregation, and lacks robustness in heterogeneous client environments. To address these challenges, we propose the Attention-Driven multi-party Collusion Attack (ADCA). During local pre-training, malicious clients decompose the global trigger to find optimal local patterns. Subsequently, these malicious clients collude to form a malicious coalition and establish a collaborative optimization mechanism within it. In this mechanism, each submits its model updates, and an attention mechanism dynamically aggregates them to explore the best cooperative strategy. The resulting aggregated parameters serve as the initial state for the next round of training within the coalition, thereby effectively mitigating the dilution of backdoor information by benign updates. Experiments on multiple FSSL scenarios and four datasets show that ADCA significantly outperforms existing methods in Attack Success Rate (ASR) and persistence, proving its effectiveness and robustness.