Intrusion detection algorithm of wireless network based on network traffic anomaly analysis

Due to the openness and sharing nature of wireless networks, they are vulnerable to various network attacks. To promptly identify and mitigate abnormal behaviors while ensuring normal operation and security, this paper proposes an algorithm for detecting compromised nodes in wireless networks based on network traffic anomaly analysis. In the proposed detection architecture, a network traffic data acquisition module mines and reconstructs real-time traffic data from wireless nodes, removing redundant information. The processed data is then fed into an anomaly analysis module, where abnormal traffic features are extracted and dimensionality-reduced via a stacked autoencoder to form standardized anomaly profiles. These features are analyzed by an intrusion detection module combining particle swarm optimization and support vector machine algorithms. Experimental results demonstrate that the algorithm efficiently extracts traffic anomalies, accurately detects attack duration and traffic volume changes in compromised nodes, and maintains a false detection rate below 6 %.