Artificial intelligence techniques have grown rapidly in recent years, and their applications in practice can be seen in many fields, ranging from facial recognition to image analysis. In the cybersecurity domain, AI-based techniques can provide better cyber defense tools and help adversaries improve methods of attack. However, malicious actors are aware of the new prospects too and will probably attempt to use them for nefarious purposes. This survey paper aims at providing an overview of how artificial intelligence can be used in the context of cybersecurity in both offense and defense.

No abstract

Recent developments in Artificial intelligence (AI) have a vast transformative potential for both cybersecurity defenders and cybercriminals. Anti-malware solutions adopt intelligent techniques to detect and prevent threats to the digital space. In contrast, cybercriminals are aware of the new prospects too and will probably try to use it in their activities. This survey aims at providing an overview on the way artificial intelligence can be used to power a malicious program that is: intelligent evasion techniques, autonomous malware, AI against itself, and applying bio-inspired computation and swarm intelligence. IntroductionFor recent years, AI is becoming an omnipresent trend. At this time, when using an online search engine, we can get over 4 billion results, which illustrates the interest of experts and the public. Interest in AI has been high for the past few years, reaching a peak in 2018. This hype is due to significant advances in the field of AI and their extensive applications in the real world.Malware is malicious software that infiltrates or damage a computer system without consent and without informing the system owner. Researchers used this term to express a variety of forms of software or program code, such as computer virus, worm, trojan horse, retrovirus, botnet [43]. Its impact on digital society is enormous, so a considerable amount of research has been done to find effective measures to prevent this pandemic. Due to the impact of malware, the community has developed technologies to counter against it. Unfortunately, there are cases where new malware spreads over the Internet, making defense solutions useless. Thus, to keep pace with malware evolution, advanced techniques like Machine Learning (ML) and Deep Learning (DL) need to be used [9]. In particular, anti-malware solutions can use various intelligent techniques, such as artificial neural networks to recognize new and unknown malware codes. Generally speaking, the evolution of malware and antimalware technologies is an ongoing tug-of-war with no end. The evolution of malware entails the development of anti-malware systems. Hence, it is important to predict, model, and confirm by experimenting with possible anti-malware software improvements to ready for new emergence threats [48].Up to the present time, researchers published various literature discussing the dynamics and spreading of malware. The most significant trend focuses on the dynamics of malware (typically based on mathematical models) as well as the study of how malware behaves in real-world networks such as computer networks, social networks, and others. The authors in [36] study the computer virus infection by adapting the epidemiologically compartmental models. They have drawn a mathematical model and identified potential edges where contagion could occur. In the meantime, the authors in [50] proposed a heterogeneous propagation model and its optimal control problem, in which they studied the combined impact of countermeasure and network topology on virus diffusion and optimal...

No abstract