Unveiling Hidden Threats: Using Fractal Triggers to Boost Stealthiness of Distributed Backdoor Attacks in Federated Learning

TL;DR

This paper introduces FTDBA, a fractal-based distributed backdoor attack in federated learning that significantly reduces poisoning volume and detection risk while maintaining high attack success rates.

Contribution

It proposes a novel fractal-triggered attack method with adaptive perturbation to improve stealthiness and efficiency in federated learning backdoor attacks.

Findings

Achieves 92.3% attack success rate with 62.4% poisoning volume

Reduces detection rate by 22.8%

Lowers KL divergence by 41.2%

Abstract

Traditional distributed backdoor attacks (DBA) in federated learning improve stealthiness by decomposing global triggers into sub-triggers, which however requires more poisoned data to maintian the attck strength and hence increases the exposure risk. To overcome this defect, This paper proposes a novel method, namely Fractal-Triggerred Distributed Backdoor Attack (FTDBA), which leverages the self-similarity of fractals to enhance the feature strength of sub-triggers and hence significantly reduce the required poisoning volume for the same attack strength. To address the detectability of fractal structures in the frequency and gradient domains, we introduce a dynamic angular perturbation mechanism that adaptively adjusts perturbation intensity across the training phases to balance efficiency and stealthiness. Experiments show that FTDBA achieves a 92.3\% attack success rate with only 62.4\% of the poisoning volume required by traditional DBA methods, while reducing the detection rate by 22.8\% and KL divergence by 41.2\%. This study presents a low-exposure, high-efficiency paradigm for federated backdoor attacks and expands the application of fractal features in adversarial sample generation.