This research recasts the network attack dataset from UNSW-NB15 as an intrusion detection problem in image space. Using one-hot-encodings, the resulting grayscale thumbnails provide a quarter-million examples for deep learning algorithms. Applying the MobileNetV2's convolutional neural network architecture, the work demonstrates a 97% accuracy in distinguishing normal and attack traffic. Further class refinements to 9 individual attack families (exploits, worms, shellcodes) show an overall 56% accuracy. Using feature importance rank, a random forest solution on subsets show the most important source-destination factors and the least important ones as mainly obscure protocols. The dataset is available on Kaggle.
翻译:这项研究将UNSW-NB15的网络攻击数据集重新定位为图像空间的入侵探测问题。 由此产生的灰度缩略图使用一热编码,为深层学习算法提供了25万个实例。 应用了移动NetV2的进化神经网络结构, 这项工作在区分正常和攻击交通方面显示了97%的精确度。 对9个攻击家庭( 开发、 蠕虫、 贝壳代码)的进一步分类改进显示了56%的总体精确度。 使用特性重要性等级, 子集的随机森林解决方案显示了最重要的源估计因素, 以及最不重要的( 主要是模糊的) 协议。 该数据集可以在 Kaggle 上查阅 。