Institutional Repository of Vilnius University
Kenksmingų HTTP užklausų aptikimas naudojant mašininio mokymosi algoritmus /
Abstract
dc:descriptionThe goal of this paper is to create machine learning models, which are capable to detect malicious HTTP requests. A review of literature for machine learning application in detection of malicious HTTP requests is performed. Different machine learning models are created using these machine learning algorithms: One class SVM, SVM, decision trees, random forest. Models were trained using two different datasets (“CSIC 2010” and “ECML/PKDD 2007”) and three feature extraction techniques were tested. “ModSecurity” web application firewall was put to test against same datasets. The comparative analysis of created models and “ModSecurity” web application firewall is performed: the highest detection rate and relatively low false positive rate was achieved by random forest algorithm on both datasets.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2021
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Virbalas, Tomas,
- Contributors dc:contributor
-
- Kybartas, Rimantas
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD107116717&prefLang=en_US