Machine learning (ML) and Deep Learning (DL) methods are being adopted rapidly, especially in computer network security, such as fraud detection, network anomaly detection, intrusion detection, and much more. However, the lack of transparency of ML and DL based models is a major obstacle to their implementation and criticized due to its black-box nature, even with such tremendous results. Explainable Artificial Intelligence (XAI) is a promising area that can improve the trustworthiness of these models by giving explanations and interpreting its output. If the internal working of the ML and DL based models is understandable, then it can further help to improve its performance. The objective of this paper is to show that how XAI can be used to interpret the results of the DL model, the autoencoder in this case. And, based on the interpretation, we improved its performance for computer network anomaly detection. The kernel SHAP method, which is based on the shapley values, is used as a novel feature selection technique. This method is used to identify only those features that are actually causing the anomalous behaviour of the set of attack/anomaly instances. Later, these feature sets are used to train and validate the autoencoder but on benign data only. Finally, the built SHAP_Model outperformed the other two models proposed based on the feature selection method. This whole experiment is conducted on the subset of the latest CICIDS2017 network dataset. The overall accuracy and AUC of SHAP_Model is 94% and 0.969, respectively.
翻译:机器学习(ML)和深学习(DL)方法正在迅速得到采用,特别是在计算机网络安全方面,特别是在欺诈检测、网络异常检测、入侵检测等计算机网络安全方面。然而,基于 ML 和 DL 模型缺乏透明度是执行这些模型的主要障碍,并因其黑箱性质而受到批评,即使结果如此巨大。可以解释的人工智能(XAI)是一个很有希望的领域,可以通过解释和解释其输出来提高这些模型的可信任性。如果基于 ML 和 DL 模型的内部工作是可以理解的,那么它可以进一步帮助改进其性能。本文的目的是显示如何使用 XAI 来解释基于 DL 模型的结果, 自动编码的模型和 DLA 。根据解释, 我们改进了计算机网络异常检测的性能。基于沙普利值的内核 SHAP 方法被作为一种新的地貌选择技术。这种方法仅用于确定那些实际导致攻击/ Adel 常规模型的异常行为特征, 本文的目的是表明如何使用 XAI 模型, 最终, 使用这些特性组数据只用于基于 AS AS ASal_ a rodeal roal ex ex ex ex ex beal beal beal beal beal be lacuild the pricuild the sal dricuilate prial drial be laimal be be be be be be be be be laut the laut the laut the sal be be be be be be be be be be be be be be laut the sal lautal drocumental drocumental drocumental drictional drictional drocumental drocumental drictional drocumental lad ladal drialdaldal drocudiadal drocuildaldal drod drial ladaldaldaldddaldaldaldaldaldaldaldaldald shadald ladaldaldal shadal lad drialdal ladaldaldaldddaldaldald ladaldal lad lad shad