A Supervised Machine Learning Based Intrusion Detection Model for Detecting Cyber-Attacks Against Computer System

Abstract

Internet usage has become essential for correspondence in almost every calling in our digital age. To protect a network, an effective intrusion detection system (IDS) is vital. Intrusion Detection System is a software application to detect network intrusion using various machine learning algorithms. The function of the expert has been lessened by machine learning approaches since knowledge is taken directly from the data. The fact that it makes use of all the features of an information packet spinning in the network for intrusion detection is weakened by the employment of various methods for detecting intrusions, such as statistical models, safe system approaches, etc. Machine learning has become a fundamental innovation for cyber security. Two of the key types of attacks that plague businesses, as proposed in this paper, are Denial of Service (DOS) and Distributed Denial of Service (DDOS) attacks. One of the most disastrous attacks on the Internet of Things (IOT) is a denial of service. Two diverse Machine Learning techniques are proposed in this research work, mainly Supervised learning. To achieve this goal, the paper represents a regression algorithm, which is usually used in data science and machine learning to forecast the future. An innovative approach to detecting is by using the Machine Learning algorithm by mining application-specific logs. Cyber security is a way of providing their customers the peace of mind they need knowing that they have secured their information and money.

Research on communication network intrusion detection method based on machine learning algorithm

“…At the same time, it needs to delete the data with attack type involved. Effectively prevent the attack data from invading other upper systems [9] .…”