Abstract:

In recent years， underwater acoustic communication network plays a crucial role in underwater information transmission. Due to the open nature of underwater communication channels， they are more prone to attacks such as interference， tempering， and eavesdropping， so that underwater acoustic communication networks face security challenges different from traditional networks. However， traditional anomaly detection methods have lower accuracy when applied to underwater acoustic networks directly. At the same time， although machine learning-based anomaly detection methods improve accuracy， they face problems such as limited datasets and poor model interpretability. Therefore， CNN-BiLSTM integrating attention mechanism was applied for anomaly attack detection in underwater acoustic networks， and WCBA （underWater CNN-BiLSTM-Attention） model was proposed. In the model， the high dimension of dataset was reduced effectively through IG-PCA （Integrated Gradient-Principal Component Analysis） feature selection algorithm， and the identification of abnormal attacks in complex underwater data was enabled by fully utilizing the spatio-temporal features of multi-dimensional matrix acoustic network traffic. Experimental results show that WCBA model provides higher accuracy and interpretability compared to other neural network models when the dataset is limited.

Key words: underwater acoustic communication network, anomaly detection, network security, feature selection, Convolutional Neural Network (CNN), attention mechanism

摘要：

近些年，水声通信网络在水下信息传输方面发挥了至关重要的作用。水下通信信道具有开放性，更易遭受干扰、欺骗和窃听等攻击，因此水声通信网络面临与传统网络不同的安全挑战。然而，传统的异常检测方法直接用于水声网络时的准确率较低，而基于机器学习的异常检测方法虽然提高了准确率，但面临数据集受限、模型可解释性较差等问题。因此，将融合注意力机制的CNN-BiLSTM用于水声网络下的异常攻击检测，并提出WCBA（underWater CNN-BiLSTM-Attention）模型。该模型通过IG-PCA（Integrated Gradient-Principal Component Analysis）特征选择算法有效降低数据集的高维度，并能充分利用多维矩阵水声通信网络流量的时空特征在复杂水声数据中识别异常攻击。实验结果表明，WCBA模型在数据集受限的情况下，相较于其他神经网络模型提供了更高的准确率，并具有较高可解释性。

关键词: 水声通信网络, 异常检测, 网络安全, 特征选择, 卷积神经网络, 注意力机制