scholarly journals Utilizing XAI Technique to Improve Autoencoder based Model for Computer Network Anomaly Detection with Shapley Additive Explanation(SHAP)

2021 ◽  
Vol 13 (6) ◽  
pp. 109-128
Author(s):  
Khushnaseeb Roshan ◽  
Aasim Zafar
Keyword(s):  
Feature Selection ◽  
Anomaly Detection ◽  
Computer Network ◽  
Feature Selection Method ◽  
Feature Selection Technique ◽  
Internal Working ◽  
Computer Network Security ◽  
Promising Area ◽  
Shapley Values ◽  
Network Anomaly Detection

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 autoencoderbut 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.

scholarly journals Network Anomaly Detection System with Optimized DS Evidence Theory

2014 ◽  
Vol 2014 ◽  
pp. 1-13 ◽  
Author(s):  
Yuan Liu ◽  
Xiaofeng Wang ◽  
Kaiyu Liu
Keyword(s):  
Anomaly Detection ◽  
Detection Rate ◽  
Computer Network ◽  
Detection System ◽  
Evidence Theory ◽  
Optimization Methods ◽  
High Detection Rate ◽  
Detection Model ◽  
Network Anomaly Detection ◽  
Anomaly Detection System

Network anomaly detection has been focused on by more people with the fast development of computer network. Some researchers utilized fusion method and DS evidence theory to do network anomaly detection but with low performance, and they did not consider features of network—complicated and varied. To achieve high detection rate, we present a novel network anomaly detection system with optimized Dempster-Shafer evidence theory (ODS) and regression basic probability assignment (RBPA) function. In this model, we add weights for each senor to optimize DS evidence theory according to its previous predict accuracy. And RBPA employs sensor’s regression ability to address complex network. By four kinds of experiments, we find that our novel network anomaly detection model has a better detection rate, and RBPA as well as ODS optimization methods can improve system performance significantly.

scholarly journals A Correlation-Change Based Feature Selection Method for IoT Equipment Anomaly Detection

2019 ◽  
Vol 9 (3) ◽  
pp. 437 ◽  
Author(s):  
Shen Su ◽  
Yanbin Sun ◽  
Xiangsong Gao ◽  
Jing Qiu ◽  
Zhihong Tian
Keyword(s):  
Feature Selection ◽  
Anomaly Detection ◽  
False Negative ◽  
Feature Selection Method ◽  
Window Size ◽  
Selection Method ◽  
Sensor Data ◽  
Data Correlation ◽  
The Right ◽  
Sensor Clustering

Selecting the right features for further data analysis is important in the process of equipment anomaly detection, especially when the origin data source involves high dimensional data with a low value density. However, existing researches failed to capture the fact that the sensor data are usually correlated (e.g., duplicated deployed sensors), and the correlations would be broken when anomalies occur with happen to the monitored equipment. In this paper, we propose to capture such sensor data correlation changes to improve the performance of IoT (Internet of Things) equipment anomaly detection. In our feature selection method, we first cluster correlated sensors together to recognize the duplicated deployed sensors according to sensor data correlations, and we monitor the data correlation changes in real time to select the sensors with correlation changes as the representative features for anomaly detection. To that end, (1) we conducted curve alignment for the sensor clustering; (2) we discuss the appropriate window size for data correlation calculation; (3) and adopted MCFS (Multi-Cluster Feature Selection) into our method to adapt to the online feature selection scenario. According to the experiment evaluation derived from real IoT equipment, we prove that our method manages to reduce the false negative of IoT equipment anomaly detection of 30% with almost the same level of false positive.

Feature selection by multi-objective optimisation: Application to network anomaly detection by hierarchical self-organising maps

2014 ◽  
Vol 71 ◽  
pp. 322-338 ◽  
Author(s):  
Emiro de la Hoz ◽  
Eduardo de la Hoz ◽  
Andrés Ortiz ◽  
Julio Ortega ◽  
Antonio Martínez-Álvarez
Keyword(s):  
Feature Selection ◽  
Anomaly Detection ◽  
Multi Objective ◽  
Network Anomaly Detection

scholarly journals A New Design of Custom Optimized Cnn-Lstm Assists to Detect Network Anomaly Using Categorical Data

2021 ◽  
Author(s):  
Kanmani R ◽  
A.Christy Jeba Malar ◽  
Roopa V ◽  
Ranjani D ◽  
Suganya R
Keyword(s):  
Feature Selection ◽  
Anomaly Detection ◽  
Categorical Data ◽  
Imbalanced Data ◽  
Experimental Result ◽  
Training Dataset ◽  
Detection Model ◽  
Effective Performance ◽  
Network Anomaly Detection ◽  
System Effectiveness

Abstract For traditional intrusion detection model, the system effectiveness is fully based on training dataset and feature selection. During feature selection, it needs more labour charge and trusted mainly on expert’s knowledge. Moreover, the training dataset contains more imbalanced data which in terms model tends to be biased. Here, an automatic approach is introduced to correct deficiency in the system. In this paper, the author proposes novel network anomaly detection (NID) build using categorical data. A model has to be designed with modified form of deep neural network primarily utilized for detecting anomaly within the network. Custom CNN-LSTM with Harris Hawks Optimization (named as custom optimized CNN-LSTM) is designed as a new classifier majorly used to detect the anomaly from word cloud to distinguish the data with effective performance. The experimental result shows that the proposed method achieves a promising output for network anomaly detection.

scholarly journals Effect on speech emotion classification of a feature selection approach using a convolutional neural network

2021 ◽  
Vol 7 ◽  
pp. e766
Author(s):  
Ammar Amjad ◽  
Lal Khan ◽  
Hsien-Tsung Chang
Keyword(s):  
Neural Network ◽  
Feature Selection ◽  
Convolutional Neural Network ◽  
Feature Selection Method ◽  
Classification Problem ◽  
Speech Emotion Recognition ◽  
Support Vector ◽  
Emotion Classification ◽  
K Nearest Neighbors ◽  
Feature Selection Technique

Speech emotion recognition (SER) is a challenging issue because it is not clear which features are effective for classification. Emotionally related features are always extracted from speech signals for emotional classification. Handcrafted features are mainly used for emotional identification from audio signals. However, these features are not sufficient to correctly identify the emotional state of the speaker. The advantages of a deep convolutional neural network (DCNN) are investigated in the proposed work. A pretrained framework is used to extract the features from speech emotion databases. In this work, we adopt the feature selection (FS) approach to find the discriminative and most important features for SER. Many algorithms are used for the emotion classification problem. We use the random forest (RF), decision tree (DT), support vector machine (SVM), multilayer perceptron classifier (MLP), and k-nearest neighbors (KNN) to classify seven emotions. All experiments are performed by utilizing four different publicly accessible databases. Our method obtains accuracies of 92.02%, 88.77%, 93.61%, and 77.23% for Emo-DB, SAVEE, RAVDESS, and IEMOCAP, respectively, for speaker-dependent (SD) recognition with the feature selection method. Furthermore, compared to current handcrafted feature-based SER methods, the proposed method shows the best results for speaker-independent SER. For EMO-DB, all classifiers attain an accuracy of more than 80% with or without the feature selection technique.

scholarly journals Opinion classification on a social network by a novel feature selection technique

2020 ◽  
Vol 20 (2) ◽  
pp. 960
Author(s):  
Atchara Choompol ◽  
Panida Songram ◽  
Phattahanaphong Chomphuwiset
Keyword(s):  
Feature Selection ◽  
Social Network ◽  
Association Rules ◽  
Information Gain ◽  
Feature Selection Method ◽  
Tuning Parameter ◽  
Computational Time ◽  
Chi Square ◽  
Feature Selection Technique ◽  
Filter Model

Most of the opinion comments on social networks are short and ambiguous. In general, opinion classification on the comments is difficult because of lacking dominant features. A feature extraction technique is therefore necessary for improving accuracy of the classification and computational time. This paper proposes an effective feature selection method for opinion classification on a social network. The proposed method selects features based on the concept of a filter model, together with association rules. Support and confidence are used to calculate the weights of features. The features with high weight are selected for classification. Unlike supports in association rules, supports in our method are normalized to 0-1 to remove outlier supports. Moreover, a tuning parameter is used to emphasize the degree of support or confidence. The experimental results show that the proposed method provides high classification efficiency. The proposed method outperforms Information Gain, Chi-Square, and Gini Index in both computational time and accuracy.

A Hierarchical Feature Selection Method Based on Classification Tree for HGU Fault Diagnosis

2014 ◽  
Vol 1037 ◽  
pp. 398-403 ◽  
Author(s):  
Xiao Yue Chen ◽  
Jian Zhong Zhou ◽  
Xiao Min Xu ◽  
Yong Chuan Zhang
Keyword(s):  
Feature Selection ◽  
Fault Diagnosis ◽  
Heuristic Search ◽  
Classification Tree ◽  
Evaluation Criteria ◽  
Feature Selection Method ◽  
Selection Method ◽  
Safe Operation ◽  
Feature Selection Technique ◽  
Hydraulic Generator

Fault diagnosis is very important to ensure the safe operation of hydraulic generator units (HGU). Because of the complexity of HGU, the vast amounts of measured data and the redundant information, the accuracy and instantaneity of fault diagnosis are severely limited. At present, feature selection technique is an effective method to break through this bottleneck. According to the specific characteristics of HGU faults, this paper puts forward a hierarchical feature selection method based on classification tree (HFSMCT). HFSMCT selects the most effective feature for each branch node through filtering evaluation criteria and heuristic search strategy, and all the selected features constitute the final feature set. Moreover, HFSMCT is easy to design and implement, and it is very prominent in computational efficiency and accuracy. The simulation results also prove that HFSMCT is very suitable for HGU fault diagnosis.

scholarly journals Feature Selection for Ridge Regression with Provable Guarantees

2016 ◽  
Vol 28 (4) ◽  
pp. 716-742 ◽  
Author(s):  
Saurabh Paul ◽  
Petros Drineas
Keyword(s):  
Feature Selection ◽  
Ridge Regression ◽  
Feature Selection Method ◽  
Feature Space ◽  
Data Sets ◽  
Real World Data ◽  
Feature Selection Technique ◽  
Worst Case ◽  
Single Set ◽  
Classification Function

We introduce single-set spectral sparsification as a deterministic sampling–based feature selection technique for regularized least-squares classification, which is the classification analog to ridge regression. The method is unsupervised and gives worst-case guarantees of the generalization power of the classification function after feature selection with respect to the classification function obtained using all features. We also introduce leverage-score sampling as an unsupervised randomized feature selection method for ridge regression. We provide risk bounds for both single-set spectral sparsification and leverage-score sampling on ridge regression in the fixed design setting and show that the risk in the sampled space is comparable to the risk in the full-feature space. We perform experiments on synthetic and real-world data sets; a subset of TechTC-300 data sets, to support our theory. Experimental results indicate that the proposed methods perform better than the existing feature selection methods.

Sign in / Sign up

Export Citation Format

Share Document