A Brief Review onDifferent Machine Learning-Based Intrusion Detection Systems
- Title
- A Brief Review onDifferent Machine Learning-Based Intrusion Detection Systems
- Creator
- Samanta S.; Sen A.P.; Mukhopadhyay D.; De S.; Bhattacharyya S.; Platos J.
- Description
- In the contemporary cybersecurity landscape, the proliferation of complex and sophisticated cyber threats necessitates the development of robust Intrusion Detection Systems (IDS) for safeguarding network infrastructures. These threats make it more challenging to maintain the communitys availability, integrity, and confidentiality. To ensure a secure network, community administrators should implement multiple intrusion detection systems (IDS) to monitor and detect unauthorized and malicious activities. An intrusion detection system examines the networks traffic by analyzing data flowing through computers to identify potential security threats or malicious activities. It alerts administrators when suspicious activities are detected. IDS generally performs two types of malicious activity detection: misuse or signature-based detection, which entails collecting and comparing information to a database of known attack signatures, and anomaly detection, which detects any behavior that differs from the standard activity and assumes it to be malicious. The proposed paper offers an overview of how different Machine Learning Algorithms like Random forest, k - Nearest Neighbor, Decision tree, Support Vector Machine, Naive Bayes, and K- means are used for IDS and how these algorithms perform on different well-known datasets, and Their accuracy and performance are evaluated and compared, providing valuable insights for future work. kNN shows an accuracy of 90.925% for Denial of Service Attacks and 98.244% for User To Root attacks. The SVM algorithm shows an accuracy of 93.051% for Probe attacks and 80.385% accuracy for remote-to-local attacks. According to our implementation, these two algorithms work better than the others. The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.
- Source
- Lecture Notes on Data Engineering and Communications Technologies, Vol-220, pp. 98-108.
- Date
- 2024-01-01
- Publisher
- Springer Science and Business Media Deutschland GmbH
- Subject
- Decision tree algorithm; Intrusion detection; kNN algorithm; Random Forest algorithm; Support vector Machine algorithm
- Coverage
- Samanta S., Department of Computer Science and Engineering, Cooch Behar Government Engineering College, West Bengal, Cooch Behar, India; Sen A.P., Department of Computer Science and Engineering, Cooch Behar Government Engineering College, West Bengal, Cooch Behar, India; Mukhopadhyay D., Department of Computer Science and Engineering, School of Engineering and Technology, Christ University, Bangalore, India; De S., Department of Computer Science and Engineering, Cooch Behar Government Engineering College, West Bengal, Cooch Behar, India; Bhattacharyya S., VSB Technical University of Ostrava, Ostrava, Czech Republic, Algebra University, Zagreb, Croatia; Platos J., VSB Technical University of Ostrava, Ostrava, Czech Republic
- Rights
- Restricted Access
- Relation
- ISSN: 23674512
- Format
- Online
- Language
- English
- Type
- Book chapter
Collection
Citation
Samanta S.; Sen A.P.; Mukhopadhyay D.; De S.; Bhattacharyya S.; Platos J., “A Brief Review onDifferent Machine Learning-Based Intrusion Detection Systems,” CHRIST (Deemed To Be University) Institutional Repository, accessed February 24, 2025, https://archives.christuniversity.in/items/show/17935.