Detection of Cyber Attacks: XSS, SQLI, Phishing Attacks and Detecting Intrusion Using Machine Learning Algorithms

Abstract

Cyber-crime is spreading throughout the world, exploiting any type of vulnerability in the cloud computing platform. Ethical hackers are primarily concerned in identifying flaws and recommending mitigation measures. In the cyber security world, there is a pressing need for the development of effective techniques. The majority of IDS techniques used today are incapable of dealing with the dynamic and complex nature of cyber-attacks on computer networks. In cyber security, machine learning approaches have been utilized to handle important concerns such as intrusion detection, XSS, SQLI, and phishing detection. Machine learning approaches have been employed in order to detect the issues such as XSS, SQLI, Phishing attacks etc. In this study XSS attack is detected using CNN approach, SQLI attack is detected using Logistic Regression approach, phishing is detected using SVM approach. In addition to the above specified attacks: DTC, BNB, KNN approaches are employed to detect the intrusion in the system. As a result, CNN approach yields 98.59% accuracy for detecting XSS attacks, Logistic Regression approach yields 92.85% accuracy for SQLI, SVM approach yields 85.62% accuracy for phishing attacks. Approaches like DTC, BNB, KNN yields an accuracy of 99.47%, 90.67% and 99.16% respectively for detecting intrusions.