Comparative Analysis of Intrusion Detection Systems and Machine Learning-Based Model Analysis Through Decision Tree
Сравнительный анализ систем обнаружения вторжений и анализ моделей на основе машинного обучения с использованием дерева решений
2023-01-01
SCID: 54.1/n5zpjmff
Discuss with AI
decision treeevasion techniquesintrusion detection systemsmachine learningnetwork intrusion detection
Figures from the paper
Abstract (AI)
Cyber-attacks pose increasing challenges in precisely detecting intrusions, risking data confidentiality, integrity, and availability. This review paper presents recent IDS taxonomy, a comprehensive review of intrusion detection techniques, and commonly used datasets for evaluation. It discusses evasion techniques employed by attackers and the challenges in combating them to enhance network security. Researchers strive to improve IDS by accurately detecting intruders, reducing false positives, and identifying new threats. Machine learning (ML) and deep learning (DL) techniques are adopted in IDS systems, showing potential in efficiently detecting intruders across networks. The paper explores the latest trends and advancements in ML and DL-based network intrusion detection systems (NIDS), including methodology, evaluation metrics, and dataset selection. It emphasizes research obstacles and proposes a future research model to address weaknesses in the methodologies. The decision tree, known for its speed and user-friendliness, is proposed as a model for detecting result anomalies, combining findings from a comparative survey. This research aims to provide insights into building an effective decision tree-based detection framework.
Key Findings
1
Decision trees are highlighted as fast and user-friendly models for detecting anomalies and supporting an effective intrusion detection framework.
2
Key IDS research challenges include reducing false positives, detecting novel threats, and addressing weaknesses exposed by adversarial evasion techniques.
3
Machine learning and deep learning approaches show potential for efficient intrusion detection, but performance depends on methodology, evaluation metrics, and dataset selection.
4
The paper reviews IDS taxonomies, intrusion detection techniques, evaluation datasets, and attacker evasion strategies affecting network security.
5
The study proposes a future research model intended to overcome methodological weaknesses in machine learning- and deep learning-based NIDS.
Research Object
machine learning- and deep learning-based network intrusion detection systems (NIDS)
Research Subject
intrusion-detection effectiveness, including accurate intruder and novel-threat detection, false-positive reduction, evasion resilience, and decision-tree-based anomaly analysis
Publication Details
Publication Date
2023-01-01
Journal
IEEE Access
Publisher
Institute of Electrical and Electronics Engineers
ISSN
2169-3536
Cited by
396
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai10
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling2014
Speech recognition with deep recurrent neural networks2013
DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks2016
A review of uncertainty quantification in deep learning: Techniques, applications and challenges2021
Survey of intrusion detection systems: techniques, datasets and challenges2019
Deep Learning Approach for Intelligent Intrusion Detection System2019
Convergence of Edge Computing and Deep Learning: A Comprehensive Survey2020
Network intrusion detection system: A systematic study of machine learning and deep learning approaches2020
Machine Learning and Deep Learning Methods for Intrusion Detection Systems: A Survey2019
Evaluating Computer Intrusion Detection Systems2015