Institutional Repository of Vilnius University
Kompiuterių tinklo duomenų srauto kopijų rinkimas, saugojimas ir jų apdorojimas mašininio mokymosi algoritmų taikymams /
Abstract
dc:descriptionThe main goal of the final work is to create a system for detecting fictitious automated connections to game servers in a computer network using machine learning algorithms. The following tasks were solved during the work: 1. To perform the analysis of the products of the bot detection systems available on the market; 2. To analyze the structure of computer network packets, their collection and storage using active computer network equipment; 3. To review the application of machine learning algorithms for the analysis of computer network packets; 4. To create an add-on for computer network packet analysis and anomaly detection in the computer network. A software solution for the detection of fictitious automated connections to a computer game server on a computer network using machine learning algorithms has been developed. The efficiency of this solution using different machine learning algorithms has been analyzed and it has been found that the Random Forest algorithm can operate with up to 100% accuracy with the datasets collected during the operation of the program.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2022
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Gabalis, Nerijus,
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:ELABAETD146238723&prefLang=en_US