“…In particular, for the anomaly detection, the following ML and DL methods were used: (a) Angle-Based Outlier Detection (ABOD) [54], [55], (b) Isolation Forest (Iforest) [56], (c) Principal Component Analysis (PCA) [57], (d) Minimum Covariance Determinant (MCD) [58], (e) Local Outlier Factor (LOF) [59], (f) DIDEROT Autoencoder [45], (g) ARIES GAN [46] and BlackBox IDS [60]. Similarly, for the anomaly classification, the subsequent methods were utilised: (a) Logistic Regression [61], (b) Linear Discriminant Analysis (LDA) [62], (c) Decision Tree Classifier [63], (d) Gaussian Naive Bayes (Gaussian NB) [64], (e) Support Vector Machine (SVM), (f) Random Forest [65], (g) Multilayer Perceptron (MLP) [66], (h) Adaptive Boosting (AdaBoost) [67], (i) Quadratic Discriminant Analysis [68], (j) Dense DNN ReLU [46] and (k) Dense DNN Tanh [46]. The DIDEROT Autoencoder and the ARIES GAN, Dense DNN Relu and Dense DNN Tanh originate from our previous works in [45] and [46], respectively.…”