Insights into anomaly-based intrusion detection systems usability. A case study using real http requests
Open Access
- 5 June 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 82-89
Abstract
Intrusion detection systems based on anomalies (A-IDS) are crucial for detecting cyberattacks, especially zero-day attacks. Numerous A-IDS proposals in the literature report excellent performance according to established metrics and settings in a laboratory. However, finding systems implementing these proposals in real-world scenarios is challenging. This work explores, through a case study, the suitability of performance metrics commonly used in the scientific literature to real-world scenarios. Our case study will consider a Web attack detector based on URIs and a real, large-scale dataset. Our results show significant limitations in the performance metrics commonly used to select the system’s operating point and its practical use in real-world scenarios.Keywords
Funding Information
- Spanish Ministry of Industry under the contract MICIN/AEI/10.13039/501100011033 (PID2020-115199RB-I00)
This publication has 18 references indexed in Scilit:
- Biblio-Us17: A Large, Realistic and Labeled Uri Dataset for Website Modelling in Anomaly-Based Intrusion Detection SystemsSSRN Electronic Journal, 2023
- Synthetic attack data generation model applying generative adversarial network for intrusion detectionComputers & Security, 2022
- A critical review of the techniques used for anomaly detection of HTTP-based attacks: taxonomy, limitations and open challengesComputers & Security, 2022
- Resampling imbalanced data for network intrusion detection datasetsJournal of Big Data, 2021
- Automatic generation of HTTP intrusion signatures by selective identification of anomaliesComputers & Security, 2015
- 100% Classification Accuracy Considered Harmful: The Normalized Information Transfer Factor Explains the Accuracy ParadoxPLOS ONE, 2014
- Imbalanced Data Learning Approaches ReviewInternational Journal of Data Mining & Knowledge Management Process, 2013
- Toward Credible Evaluation of Anomaly-Based Intrusion-Detection MethodsIEEE Transactions on Systems, Man and Cybernetics, Part C (Applications and Reviews), 2010
- Outside the Closed World: On Using Machine Learning for Network Intrusion Detection2010
- Anomaly-based network intrusion detection: Techniques, systems and challengesComputers & Security, 2009