Ensemble-based Machine Learning Techniques for Attack Detection

Internet and web services are fundamental use in our individual daily life. Individuals can learn and work very well through the Internet. As Internet development increases, the possibility of attack and security issues is also growing; this is a critical problem. It is challenging to recognize various assaults, particularly those that have never been seen, which is a major issue that should be tended to right away. Most detection systems are based on machine learning, AI, deep learning, etc for attack detection. This paper proposed ensemble learning for attack detection based on five different classifiers: regression classifier, Decision tree classifier, Kneighber classifier, SVM classifier, and Gnb classifier. The proposed method enhance the accuracy of recognition attack. The accuracy of the recommend algorithm is 0.981%.