An intrusion detection system, often known as IDS, is primarily used to gather and analyze data regarding security events that occur in computer systems and networks. Its subsequent purpose is to either prevent these events from happening or notify them to the administrator of the system. As a result of the increasing number of attacks carried out by attackers, the users’ level of mistrust on the Internet has increased. Attacks that cause denial of service are a major violation of security. This article presents a particle swarm optimization and AdaBoost-based intrusion detection system. In this system, chatbot receives network traffic as input, and features of input dataset are selected using particle swarm optimization algorithm. A classification model is trained and tested. AdaBoost, KNN, and naïve Bayes algorithm are used to classify and detect malware-related records. NSL KDD dataset is used in the experimental work. PSO-AdaBoost achieves the highest accuracy, precision, and recall for intrusion detection and classification. The output of a chatbot is a language that is either normal or benign.
