2020/12/09 by Rony Chowdhury Ripan, Ripan, Rony Chowdhury, Iqbal H. Sarker +11
Computer Science · #Advanced Malware Detection Techniques #Anomaly Detection Techniques and Applications #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Network Security and Intrusion Detection
paper · pdf · doi:10.48550/arxiv.2101.03141
openalex publication_date 2020/12/09 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28
Cybersecurity has recently gained considerable interest in today's security\nissues because of the popularity of the Internet-of-Things (IoT), the\nconsiderable growth of mobile networks, and many related apps. Therefore,\ndetecting numerous cyber-attacks in a network and creating an effective\nintrusion detection system plays a vital role in today's security. In this\npaper, we present an Isolation Forest Learning-Based Outlier Detection Model\nfor effectively classifying cyber anomalies. In order to evaluate the efficacy\nof the resulting Outlier Detection model, we also use several conventional\nmachine learning approaches, such as Logistic Regression (LR), Support Vector\nMachine (SVM), AdaBoost Classifier (ABC), Naive Bayes (NB), and K-Nearest\nNeighbor (KNN). The effectiveness of our proposed Outlier Detection model is\nevaluated by conducting experiments on Network Intrusion Dataset with\nevaluation metrics such as precision, recall, F1-score, and accuracy.\nExperimental results show that the classification accuracy of cyber anomalies\nhas been improved after removing outliers.\n