arXiv:2504.18771cs.LGcs.CR2025-04被引 1

对比多种机器学习模型在网络安全异常检测中的表现,发现XGB和MLP更优。

Performance of Machine Learning Classifiers for Anomaly Detection in Cyber Security Applications

  • 使用XGB、MLP等模型结合过采样策略处理不平衡数据。
  • 在含10%-50%缺失数据下,迭代插补效果接近均值中位数但效率低。
  • 实验结果可复现,代码开源适合安全领域研究者参考。

本研究在两个不平衡的公开数据集(KDDCUP99 和 Credit Card Fraud 2013)上实证评估了多种机器学习模型在网络安全异常检测中的表现。采用80/20训练测试划分,包含数据预处理、模型训练与评估全过程。测试模型包括eXtreme Gradient Boosting(XGB)、多层感知机(MLP)、生成对抗网络(GAN)、变分自编码器(VAE)以及多目标生成对抗主动学习(MO-GAAL),其中XGB和MLP进一步结合随机过采样(ROS)和自适应步进集成(SPE)。评估采用5折交叉验证,并使用均值、中位数及迭代插补(IterativeImputer)进行缺失值处理,覆盖10%、20%、30%和50%缺失率。结果显示,XGB与MLP在各类指标上优于生成模型;迭代插补性能与均值/中位数相当,但在大规模数据集上因计算复杂度高、耗时长而不推荐使用。相关代码已公开于GitHub(github.com/markushaug/acr-25)。

原文摘要 · Abstract (English)

This work empirically evaluates machine learning models on two imbalanced public datasets (KDDCUP99 and Credit Card Fraud 2013). The method includes data preparation, model training, and evaluation, using an 80/20 (train/test) split. Models tested include eXtreme Gradient Boosting (XGB), Multi Layer Perceptron (MLP), Generative Adversarial Network (GAN), Variational Autoencoder (VAE), and Multiple-Objective Generative Adversarial Active Learning (MO-GAAL), with XGB and MLP further combined with Random-Over-Sampling (ROS) and Self-Paced-Ensemble (SPE). Evaluation involves 5-fold cross-validation and imputation techniques (mean, median, and IterativeImputer) with 10, 20, 30, and 50 % missing data. Findings show XGB and MLP outperform generative models. IterativeImputer results are comparable to mean and median, but not recommended for large datasets due to increased complexity and execution time. The code used is publicly available on GitHub (github.com/markushaug/acr-25).

异常检测机器学习网络安全数据不平衡

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。