Sudhanshu Sekhar Tripathy, Bichitrananda Behera
This paper reviews various datasets and machine learning methods for intrusion detection systems, highlighting advances and challenges in the field.
Intrusion Detection Systems (IDS) are crucial for protecting computer networks from unauthorized access and threats. As technology advances, ensuring the security of systems and networks becomes increasingly important. This paper reviews how machine learning techniques, using popular datasets, can improve the accuracy of IDS by distinguishing between normal and suspicious network activity. The authors analyze different machine learning algorithms and datasets, providing insights into their effectiveness and the challenges they face in cybersecurity applications.
