融合CNN-BiGRU和注意力机制的网络入侵检测模型OACSTPCD
A Network Intrusion Detection Model Integrating CNN-BiGRU and Attention Mechanism
为提高网络入侵检测模型特征提取能力和分类准确率,提出了一种融合双向门控循环单元(CNN-BiGRU)和注意力机制的网络入侵检测模型.使用CNN有效提取流量数据集中的非线性特征;双向门控循环单元(BiGRU)提取数据集中的时序特征,最后融合注意力机制对不同类型流量数据通过加权的方式进行重要程度的区分,从而整体提高该模型特征提取与分类的性能.实验结果表明:其整体精确率比双向长短期记忆网络(BiLSTM)模型提升了2.25％.K折交叉验证结果表明:该模型泛化性能良好,避免了过拟合现象的发生,印证了该模型的有效性与合理性.
To enhance the feature extraction capabilities and classification accuracy of the network intrusion detection model,a network intrusion detection model integrating CNN-BiGRU(Convolutional Neural Network-Bi-directional Gated Recurrent Unit)and attention mechanism is proposed.CNN is employed to effectively extract nonlinear features from traffic datasets,while BiGRU extracts time-series features.The attention mechanism is then integrated to differentiate the importance of different types of traffic data through weighted means,thereby improvingthe overall performance of the model in feature extraction and classification.The experimental results indicate that the overall accuracy rate is 2.25％higher than that of the BiLSTM(Bi-directional Long Short-Term Memory)model.K-fold cross-validation results demonstrate that the proposed model's good generalization performance,avoiding the occurrence of over-fitting phenomenon,and affirming its effectiveness and rationality.
杨晓文;张健;况立群;庞敏
中北大学计算机科学与技术学院 太原 030051||机器视觉与虚拟现实山西省重点实验室 太原 030051||山西省视觉信息处理及智能机器人工程研究中心 太原 030051
计算机与自动化
网络入侵检测卷积神经网络双向门控循环单元注意力机制深度学习
network intrusion detectionconvolutional neural networkbidirectional gated recurrent unitattention mechanismdeep learning
《信息安全研究》 2024 (003)
202-208 / 7
国家自然科学基金项目(62272426,62106238);山西省科技成果转化引导专项(202104021301055)
评论