A Comparative Study of AI Algorithms for Anomaly-based Intrusion Detection

Abstract

The internet's quick development has brought numerous advantages, but it has also had some negative effects. Some of the drawbacks of the internet's incredible growth includes Cybersecurity risks, The internet has made it easier for hackers to access sensitive information, leading to an increase in cyber-attacks and data breaches. Privacy concerns, the internet has made it easier for companies to collect and use personal data, which has raised concerns about privacy. Disinformation, the internet has made it easier to spread misinformation and disinformation, which can have serious consequences for individuals and society. Intrusion detection systems (IDS) are important in the real world because they can help detect and prevent cyber-attacks, which can have serious consequences for individuals, organizations, and governments. Some of the benefits of IDS in the real world are Early Detection, IDS can detect suspicious activity or policy violations as they happen, allowing for early intervention and preventing attacks from causing significant harm. Alerting, IDS can alert security administrators about potential threats, enabling them to take appropriate action. Automated Response, IDS can be configured to take automated action when it detects a threat, such as blocking the source of the attack or isolating the affected system. Compliance, IDS can help organizations meet regulatory compliance requirements by providing visibility into network activity and detecting potential policy violations. Improved Security, by detecting and preventing attacks, IDS can improve overall security and reduce the risk of statistics breaches and other cyber threats. Overall, IDS is a crucial tool for maintaining the security of a computer system or network in the real world. The major objective of this study is to provide an in-depth analysis of recent trends and advancements in ML and DL-based NIDS solutions.