Intrusion Detection System for Dual Route Deep Capsule Network
-
摘要: 深度学习与入侵检测相结合已成为当今网络空间安全的热点话题，面临不稳定的网络安全局势，如何能够准确检测出异常流量是入侵检测的重要任务.入侵数据中的每一条样本包含着多个特征，但并不是每一个特征都会决定样本的最终性质，并且某些特征反而会影响模型的判断能力.为了解决这个问题，提出了一种基于残差的双重路由深层胶囊网络的入侵检测模型.该模型使用深层胶囊网络，增强对特征的识别提取，可提取出更高维度的数据特征；使用混合注意力机制对原始数据进行处理，使模型着重关注影响因素大的特征；通过双重路由算法多方位捕捉基于向量表示的特征，并将特征进行聚类；采取残差连接和设置噪音胶囊2个策略来稳定动态路由的过程，以减轻噪音特征的干扰.最后在NSL-KDD数据集和CICIDS2017数据集上进行实验，结果表明准确率最高可达90.31%和99.23%.Abstract: The combination of deep learning and intrusion detection has become a hot topic in cyberspace security. In unstable network security situation, how to accurately detect abnormal traffic is an important task for intrusion detection. Each sample in the intrusion data contains multiple features, but not every feature can determine the final nature of the sample. Some features will even affect the judgment ability of the model. To solve this problem, an intrusion detection model based on residuals of a double routing deep capsule network is proposed. The model uses a deep capsule network to enhance the identification and extraction of features, which can extract higher dimensional data features. A hybrid attention mechanism is used to process the raw data so that the model focuses on features with high impact factors. The model captures the features based on vector representation and clusters the features in multiple directions by a dual routing algorithm. It adopts two strategies, namely residual connectivity and noise capsules, to stabilize the dynamic routing process to mitigate the interference of noisy features. Finally, experiments are conducted on the NSL-KDD dataset and CICIDS2017 dataset, and the results show that the accuracy is up to 90.31% and 99.23%, respectively.
-
Keywords:
- intrusion detection /
- mixed attention /
- dynamic routing /
- security in cyberspace /
- capsule network
-
-
期刊类型引用(8)
1. 王晶晶，王延昊，姜文君，曾一夫，祝团飞. 时序图流上的快速子图近似计数算法. 计算机研究与发展. 2025(03): 709-719 . 
本站查看
2. 李源，林秋兰，陈安之，杨国利，宋威，王国仁. 基于树分解的时序最短路径计数查询算法. 计算机应用. 2024(08): 2446-2454 . 百度学术
3. 李艳红，毛德权，欧昱宏，曹阳. 考虑偏好的空间文本对象多目标最短路径查询. 中南民族大学学报(自然科学版). 2024(05): 642-649 . 百度学术
4. 轩瑞，陈磊，石海鹤. 图类算法可重用设计及其实现. 江西师范大学学报(自然科学版). 2023(01): 52-60 . 百度学术
5. 张艳秋，黎邓根，王民安，陶翠. 列车自动监控系统调度路径查找方法及其应用. 控制与信息技术. 2023(01): 119-124 . 百度学术
6. 杜明，郝燕，周军锋，谭玉婷. 一种高效的周期团挖掘方法. 计算机工程. 2023(04): 68-76 . 百度学术
7. 邓超，陈志，张欣，陆史堃，刘迪，张云彬，叶朝文，李派禹，许良本，肖骏，郑传增. 卷烟零售终端走访路径规划算法集成与应用. 中国烟草学报. 2023(03): 94-103 . 百度学术
8. 金浩宇，霍宏，方涛. 时序优先级约束的时序模式图强模拟匹配. 计算机技术与发展. 2023(06): 88-94 . 百度学术
其他类型引用(8)
计量
- 文章访问数: 366
- HTML全文浏览量: 3
- PDF下载量: 195
- 被引次数: 16
下载:
