Loading...
Ismatha Begum is an Assistant Professor in the Department of Information Technology at Guru Nanak Institute of Technology, India. Her contribution focuses on intelligent intrusion detection and machine learning applications in cybersecurity.
The cybersecurity threat landscape has grown dramatically as a result of the Internet of Things (IoT), cloud computing, software-defined networking, 5G/6G networks, and interconnected digital services. When it comes to spotting illegal activity, hostile traffic, strange behaviour, and possible security breaches, intrusion detection systems, or IDSs, are essential. Conventional signature-based intrusion detection systems (IDSs) may have trouble identifying new and quickly changing threats, but they are effective against existing attacks. By identifying patterns in network traffic, system behaviour, and security events, machine learning (ML) offers a clever substitute. The principles of machine learning-based intrusion detection, IDS architectures, data preprocessing, feature engineering, supervised and unsupervised learning, deep learning, anomaly detection, ensemble techniques, real-time detection, explainable AI, federated learning, and security challenges are all covered in this chapter. Performance evaluation, benchmark datasets, applications, case studies, and future research objectives for creating intelligent and adaptive cybersecurity systems are also covered in this chapter.