ABSTRACT
The introduction of the Internet to the mainstream through platforms like e-Commerce, online banking, health system, social media, etc., becomes a part of the large population for executing their broad categories of tasks. It also indicates that the Internet becomes the data hub that provides a good place for attackers to execute malicious intent for personal and professional benefits. The Covid-19 global pandemic has witnessed a surge of cyber-attacks that resulted in massive loss of privacy, reputation, and economics. Protecting the Internet using the security tools at different levels is one of the most critical challenges in the cyber security paradigm. The Intrusion Detection System (IDS) is one of the popular approaches for protecting the system or network from different known and unknown cyber-attacks. Several existing approaches are designing their IDS models by applying Machine learning (ML), Deep learning(DL), and ensemble techniques for improving the detection performance and for handling the higher dimensional features of attack datasets. This chapter discusses the state-of- the-art techniques proposed in the past couple of years to design IDS for preventing cyber-attacks. This work provides a broader range of state-of-the-arts that covers IDS methods for known and unknown cyber-attacks with research gap analysis.
