SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

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. Experim

Read original source ↗ Open in workspace

recordType

paper

region

Global