SOURCE-LINKED INTELLIGENCE

Fine-grained Distributed Backdoor Attacks in Federated Learning

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Federated learning, as a privacy-preserving distributed machine learning paradigm, faces significant threats from backdoor attacks. Compared to centralized attacks, distributed backdoor attacks are more harmful but require more poisoned samples to compensate for the loss of trigger strength due to decomposition. Fixed trigger patterns are also easily detected by robust aggregation algorithms, increasing the risk of attack exposure. To address these challenges, we propose a fine-grained distributed backdoor attack framework (FDBA). This framework uses dynamic trigger generation and embedding ve

Read original source ↗ Open in workspace

recordType

paper

region

Global