TASER: Task-Aware Spectral Energy Refine for Backdoor Suppression in UAV Swarms Decentralized Federated Learning

2026-03-10

AI Summary

This work addresses the challenge of defending against stealthy backdoor attacks in decentralized federated learning for drone swarms, which evade detection by conventional anomaly detection methods. To this end, the authors propose a lightweight spectral defense framework that exploits, for the first time, the concentration of backdoor-related gradients in the frequency domain. By employing a task-aware spectral energy refinement strategy, the method preserves frequency components essential to the main task while discarding others, thereby structurally disrupting backdoor implantation. Notably, the approach operates efficiently in resource-constrained decentralized settings without requiring global coordination or complex detection mechanisms. Experimental results demonstrate that the proposed defense reduces the success rate of stealthy backdoor attacks to below 20% while limiting the degradation in main task accuracy to less than 5%.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Computer Vision: Adversarial Attacks & Robustness
• Multiagent Systems: Adversarial Agents

Application Category

• Security and Privacy: Cyber-crime defenses and forensics
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

As backdoor attacks in UAV-based decentralized federated learning (DFL) grow increasingly stealthy and sophisticated, existing defenses have likewise escalated in complexity. Yet these defenses, which rely heavily on outlier detection, remain vulnerable to carefully crafted backdoors. In UAV-DFL, the lack of global coordination and limited resources further render outlier-based defenses impractical. Against this backdrop, gradient spectral analysis offers a promising alternative. While prior work primarily leverages low-frequency coefficients for pairwise comparisons, it neglects to analyze the intrinsic spectral characteristics of backdoor gradients. Through empirical analysis of existing stealthy attacks, we reveal a key insight: the more effort attackers invest in mimicking benign behaviors, the more distinct the spectral concentration becomes. Motivated by this, we propose Task-Aware Spectral Energy Refine (TASER) -- a decentralized defense framework. To our knowledge, this is the first efficient backdoor defense that utilizes spectral concentration instead of complex outlier detection, enabling mitigation of stealthy attacks by structurally disrupting the backdoor task. To suppress the backdoor task, TASER preserves main-task-relevant frequency coefficients and discards others. We provide theoretical guarantees and demonstrate through experiments that TASER remains effective against stealthy backdoor attacks that bypass outlier-based defenses, achieving attack success rate below 20% and accuracy loss under 5%.

Problem

• backdoor attacks
• UAV swarms
• decentralized federated learning
• spectral analysis
• defense

Innovation

• spectral concentration
• backdoor suppression
• decentralized federated learning
• task-aware refinement
• gradient spectral analysis