Budgeted Indirect Adversarial Attack on Graph-Based Anomaly Detection in Sensor Networks

2025/09/22 by Sanju Xaviar, Omid Ardakanian, Xaviar, Sanju +1
Computer Science · #Anomaly Detection Techniques and Applications #Network Security and Intrusion Detection #Security in Wireless Sensor Networks #cs.LG

paper · pdf · doi:10.48550/arxiv.2509.17987

openalex publication_date 2025/09/22 · openalex created_date 2025/10/16 · openalex updated_date 2026/07/28

Abstract

Graph Neural Networks (GNNs) have emerged as powerful models for anomaly detection in sensor networks, particularly when analyzing multivariate time series. In this work, we introduce BETA, a novel indirect evasion attack targeting such GNN-based detectors, where the attacker is constrained to perturb sensor readings from a limited set of nodes, excluding the target sensor, with the goal of either suppressing a true anomaly or triggering a false alarm at the target node. BETA uses a graph explanatory model combined with a centrality-based pruning strategy to identify the most influential nodes, subsequently injecting carefully crafted adversarial perturbations into their features. Extensive experiments on three real-world sensor network datasets show that BETA consistently outperforms baseline attack strategies while operating under realistic constraints, reducing the F1-score of state-of-the-art GNN-based detectors by 36.07 to 50.45% on average.

Citations

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• One Pixel Attack for Fooling Deep Neural Networks

Related

• Graph Neural Network-Based Anomaly Detection in Multivariate Time Series
• Edge Conditional Node Update Graph Neural Network for Multi-variate Time Series Anomaly Detection
• CONTINUUM: Detecting APT Attacks through Spatial-Temporal Graph Neural Networks
• GUAP: Graph Universal Attack Through Adversarial Patching
• Advancing Cyber-Attack Detection in Power Systems: A Comparative Study of Machine Learning and Graph Neural Network Approaches