Abstract
Pervasive growth and usage of the Internet and mobile applications have expanded cyberspace. The cyberspace has become more vulnerable to automated and prolonged cyberattacks. Cyber security techniques provide enhancements in security measures to detect and react against cyberattacks. The previously used security systems are no longer sufficient because cybercriminals are smart enough to evade conventional security systems. Conventional security systems lack efficiency in detecting previously unseen and polymorphic security attacks. Machine learning (ML) techniques are playing a vital role in numerous applications of cyber security. However, despite the ongoing success, there are significant challenges in ensuring the trustworthiness of ML systems. There are incentivized malicious adversaries present in the cyberspace that are willing to game and exploit such ML vulnerabilities. This paper aims to provide a comprehensive overview of the challenges that ML techniques face in protecting cyberspace against attacks, by presenting a literature on ML techniques for cyber security including intrusion detection, spam detection, and malware detection on computer networks and mobile networks in the last decade. It also provides brief descriptions of each ML method, frequently used security datasets, essential ML tools, and evaluation metrics to evaluate a classification model. It finally discusses the challenges of using ML techniques in cyber security. This paper provides the latest extensive bibliography and the current trends of ML in cyber security.
Highlights
The Internet is increasingly becoming a widely utilized source of both information and services
We have provided a brief description of machine learning techniques, and how machine learning techniques have been, or could be, used to detect and classify cyberattacks such as intrusion detection, malware detection, and spam detection on both computer networks and mobiles or smartphones devices
We have provided a graphical summary of major components of cyber security and available machine learning techniques to fight against these attacks on cyberspace
Summary
The Internet is increasingly becoming a widely utilized source of both information and (online) services. Our work presented commonly used ML tools, security datasets, graphical summary of significant components of cyber security and available ML techniques to fight against threats and attacks on cyberspace, and future challenges such as trustworthiness and adversarial machine learning under one umbrella. COMMONLY USED SECURITY DATASETS Malicious activities are performed on the computer and mobile networks to disrupt, deny, and destroy the data and services available These activities involve network attacks, phishing, spams, and the spreading of malware on vital information available on networks. The random forest has applications in the literature, such as to measure the volume of spam [217] and in intrusion detection [218] It gives better performance on non-linear problems and takes less computation cost during the training phase of the model. CoreML [270], ncnn [271], and DeepSence [272] are recommended DL platforms for mobile devices
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
