Machine learning techniques for accurate classification and detection of intrusions in computer network

An incursion into the computer network or system in issue occurs whenever there is an attempt made to circumvent defences that are place. Training and examination two basic components make up intrusion detection (IDS) each one may be analysed separately. During training, a number of distinct models built, which able distinguish between normal abnormal behaviours included within dataset. This article proposes combination ant colony optimization (ACO) firefly approach for feature selection. The final outcome giving careful thought selection features will eventually result greater accuracy categorisation. When classifying various sorts features, we use wide variety machine learning (ML) algorithms, including AdaBoost, gradient boost, Bayesian (BN), amongst others. tests assessments data obtained from three datasets, namely NSL-KDD, UNSW-NB15, CICIDS 2017. degree performance individual broken down its component parts, include F1 score, accuracy, precision, recall. Gradient boost performs far better when it comes recognising incursions.