CACTUS: Mask-Guided Semantic Clean-Label Backdoors in Decentralized Federated Learning

2026-09-02

AI Summary

研究提出CACTUS方法，通过掩码引导的语义对转换解决去中心化联邦学习中后门植入弱化的问题，增强跨聚合轮次的攻击成功率。

Abstract

Semantic triggers in federated learning (FL) can be less conspicuous than synthetic patches, but sample-dependent placement may weaken backdoor implantation across aggregation rounds. This challenge is compounded in decentralized FL (DFL), where topology-dependent peer aggregation repeatedly mixes local models. CACTUS converts label-consistent semantic pairs into target-directed representation shifts. Mask-guided, modality-specific operators isolate trigger effects, couple them across samples, and apply the shifts counterfactually to clean non-target embeddings before peer aggregation. Experiments cover speech, text, tabular, and image tasks under nine aggregation rules. With 30\% malicious nodes, CACTUS reaches a nine-rule mean attack success rate (ASR) of 51.2\% on Speech Commands and the highest nine-rule mean ASR among evaluated attacks on three of four modalities. Sensitivity analyses show that ASR varies with network topology and increases with the malicious-node ratio. These results indicate that CACTUS can propagate backdoors through repeated DFL aggregation.

Problem

• Decentralized Federated Learning
• Semantic Triggers
• Backdoor Implantation

Innovation

• Mask-Guided
• Semantic Triggers
• Decentralized Federated Learning
• Representation Shifts
• Backdoor Propagation