Comparative Analysis of Machine and Deep Learning for Cyber Security

Cyber crime is a growing problem that exploits various vulnerabilities in computing environments due to the widespread Internet applications, Internet-connected systems, and the large volume and diversity of data, making it more vulnerable to continued and automated cyber attacks. Research academia, ethical hackers, and industry are focusing on identifying vulnerabilities and recommending mitigation strategies. Traditional cyber security strategies are no longer effective in detecting new attacks, and technological advancements allow attackers to develop sophisticated attack strategies that evade current security systems. As a result, there is a growing need for advanced technologies and effective techniques to combat emerging cyber threats. To address this, machine learning (ML) and deep learning (DL) techniques have emerged as critical tools in enhancing cyber security. However, ML and DL techniques easily detect cyber crime and abnormal data packets. This chapter presents comprehensive study about ML and DL techniques to detect possible cyber attacks. However, ML and DL models are quite efficient to identify cyber threats. More interestingly, this research study is having limitations related to ML and DL techniques, which can be utilized for IDS, spam, malware, and fake page detection. Also, comprehensive comparative analysis is performed using ML and DL to provide solutions regarding cyber security. Finally, the chapter discusses the future trends of ML and DL for cyber security.