用β-VAE的隐空间和重构误差做无监督网络异常检测
Unsupervised Anomaly Detection in NSL-KDD Using $β$-VAE: A Latent Space and Reconstruction Error Approach
- 通过β-VAE构建隐空间，计算测试样本与训练数据投影的距离
- 隐空间方法在NSL-KDD数据集上表现优于传统重构误差
- 适合对无标签网络流量异常检测感兴趣的工程师
随着工业技术与信息技术深度融合，入侵检测系统的重要性日益凸显。本文在NSL-KDD数据集上探索了基于β-变分自编码器的无监督异常检测方法，比较了两种策略：利用隐空间结构，通过测量测试样本与训练数据投影之间的距离；以及使用重构误差作为传统的异常检测指标。实验结果表明，在无监督场景下，隐空间方法在分类任务中更具优势，为网络异常检测提供了有效思路。
原文摘要 · Abstract (English)
As Operational Technology increasingly integrates with Information Technology, the need for Intrusion Detection Systems becomes more important. This paper explores an unsupervised approach to anomaly detection in network traffic using $β$-Variational Autoencoders on the NSL-KDD dataset. We investigate two methods: leveraging the latent space structure by measuring distances from test samples to the training data projections, and using the reconstruction error as a conventional anomaly detection metric. By comparing these approaches, we provide insights into their respective advantages and limitations in an unsupervised setting. Experimental results highlight the effectiveness of latent space exploitation for classification tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。