Botnet Detection using Machine Learning
| Autor: | S Jayadev, K B Aswathi, Remya Krishnan, Nandana Krishna, Greeshma Sarath |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Software_OPERATINGSYSTEMS
Computer science business.industry ComputerSystemsOrganization_COMPUTER-COMMUNICATIONNETWORKS Botnet Internet security computer.software_genre Flow network Machine learning Support vector machine ComputingMilieux_MANAGEMENTOFCOMPUTINGANDINFORMATIONSYSTEMS Recurrent neural network Server Malware Unsupervised learning Artificial intelligence business computer |
| Zdroj: | ICCCNT |
| DOI: | 10.1109/icccnt51525.2021.9579508 |
| Popis: | A bot is a computer that has been affected through a malware infection and can be controlled distantly by a cyber-criminal. The cyber-criminal would be able to utilize the bot to dispatch more assaults. A botnet is a collection of such bot controlled by a cyber-criminal Infected group of computers creates a botnet on the global network. Bots are controlled by bot-master via Control & Command servers. Data breach and internet security are the main concern nowadays as it is becoming dangerous day by day. Inappropriate control of the network is possible by sending malicious botnets to the network. Once the botnets are detected in the network, they should be eliminated as soon as possible. Machine Learning plays a vital role in botnet detection and has been used for researches in this field. This paper is a comparative study of the detection of botnets from network flow data using supervised and unsupervised machine learning algorithms, including Support Vector Machine (SVM), Random Forest, K-Nearest Neighbors (KNN), K-Means, Principal Component Analysis (PCA), and Recurrent Neural Networks (RNN). |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|