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.

翻译：联邦自监督学习（FSSL）融合了分布式训练的隐私优势与自监督学习利用未标记数据的能力，在各个应用中展现出巨大潜力。然而，近期研究表明FSSL同样易受后门攻击。现有攻击方法受限于其触发器设计，通常采用全局统一的触发器，这类触发器易于被检测、在聚合过程中易被稀释，且在异构客户端环境中缺乏鲁棒性。为应对这些挑战，我们提出了注意力驱动的多方共谋攻击（ADCA）。在本地预训练阶段，恶意客户端将全局触发器分解以寻找最优的本地模式。随后，这些恶意客户端共谋形成一个恶意联盟，并在联盟内部建立协作优化机制。在该机制中，每个客户端提交其模型更新，并通过注意力机制动态聚合这些更新，以探索最佳协作策略。由此产生的聚合参数将作为联盟内下一轮训练的初始状态，从而有效缓解良性更新对后门信息的稀释作用。在多种FSSL场景及四个数据集上的实验表明，ADCA在攻击成功率（ASR）和持久性方面显著优于现有方法，证明了其有效性与鲁棒性。