• Home
  • Search
  • Automatic Clustering of Malicious IP Flow Records Using Unsupervised Learning
  • Cite Icon2
  • https://doi.org/10.1007/978-3-319-54380-2_5Copy DOI Icon

Automatic Clustering of Malicious IP Flow Records Using Unsupervised Learning

  • Jan 1, 2017
  • Muhammad Fahad Umer +1 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Anomaly based intrusion detection systems classify network traffic into normal and malicious categories. The intrusion detection system raises an alert when maliciousness is detected in the traffic. A security administrator inspects these alerts and takes corrective action to protect the network from intrusions and unauthorized access. Manual inspection of the alerts is also necessary because anomaly based intrusion detection systems have a high false positive rate. The alerts can be in very large number and their manual inspection is a challenging task. We propose an extension for anomaly based intrusion detection system which automatically groups malicious IP flows into different attack clusters. Our technique creates attack clusters from a training set of unlabeled IP flows using unsupervised learning. Every attack cluster consists of malicious IP flows which are similar to each other. We analyze IP flows in every cluster and assign an attack label to them. After the clusters are created, an incoming malicious IP flow is compared with all clusters and the label of the closest cluster is assigned to the IP flow. The intrusion detection system uses labeled flows to raise consolidated anomaly alert for a set of similar IP flows. This approach significantly reduces the overall number of alerts and also generates a high-level map of attack population. We use unsupervised learning techniques for automatic clustering of IP flows. Unsupervised learning is advantageous over supervised learning because the availability of a labeled training set for supervised learning is not always guaranteed. Three unsupervised learning techniques, k-means, self-organizing maps (SOM) and DBSCAN are considered for clustering of malicious IP flows. We evaluated our technique on a flow-based data-set containing different types of malicious flows. Experimental results show that our scheme gives good performance and places majority of the IP flows in correct attack clusters.

Similar Papers
  • PDF
  • Research Article
  • Citations1

Towards Multi-Stage Intrusion Detection using IP Flow Records

  • Jan 01, 2016
  • International Journal of Advanced Computer Science and Applications
  • Muhammad Fahad Umer +2
  • PDF
  • Research Article
  • Citations438

Benchmarking of Machine Learning for Anomaly Based Intrusion Detection Systems in the CICIDS2017 Dataset

  • Jan 01, 2021
  • IEEE Access
  • Ziadoon Kamil Maseer +4
  • Conference Article
  • Citations5

Preventing the Mistraining of Anomaly-Based IDSs through Ensemble Systems

  • Jun 01, 2014
  • Conor Fellin +1
  • Conference Article
  • Citations29

Anomaly-based Intrusion Detection System Using Fuzzy Logic

  • Jul 14, 2021
  • Mohammad Almseidin +2
  • Research Article
  • Citations1

Artificial Intelligence Based Multi-Layer Approach for Finding Unknown Attacks in Cloud Network by Using Hybrid Intrusion Detection

  • Sep 09, 2024
  • Indian Journal Of Science And Technology
  • D Rajagopal +1
  • Research Article
  • Citations33

Using response action with intelligent intrusion detection and prevention system against web application malware

  • Nov 10, 2014
  • Information Management & Computer Security
  • Ammar Alazab +4
  • Book Chapter
  • Citations21

Database Intrusion Detection Using Role Profiling with Role Hierarchy

  • Jan 01, 2009
  • Garfield Zhiping Wu +2
  • Research Article
  • Citations4

A Comparative Analysis of Signature-Based and Anomaly-Based Intrusion Detection Systems

  • Jun 03, 2025
  • International Journal of Latest Technology in Engineering Management & Applied Science
  • Vasudev Karthik Ravindran +2
  • Conference Article
  • Citations24

FPGA Hardware Acceleration Framework for Anomaly-based Intrusion Detection System in IoT

  • Aug 01, 2021
  • Duc-Minh Ngo +3
  • PDF
  • Research Article
  • Citations20

HH-NIDS: Heterogeneous Hardware-Based Network Intrusion Detection Framework for IoT Security

  • Dec 26, 2022
  • Future Internet
  • Duc-Minh Ngo +6
  • Conference Article
  • Citations4

A novel hybrid automatic intrusion detection system using machine learning technique for anomalous detection based on traffic prediction

  • Apr 05, 2023
  • D Vinod +1
  • Conference Article
  • Citations6

Establishing a secure routing in MANET using a hybrid intrusion detection system

  • Dec 01, 2014
  • N Indira
  • PDF
  • Research Article
  • Citations79

Anomaly detection optimization using big data and deep learning to reduce false-positive

  • Aug 31, 2020
  • Journal of Big Data
  • Khloud Al Jallad +2
  • PDF
  • Research Article
  • Citations110

Network Intrusion Detection Based on Novel Feature Selection Model and Various Recurrent Neural Networks

  • Apr 03, 2019
  • Applied Sciences
  • Thi-Thu-Huong Le +2
  • Book Chapter
  • Citations5

Developing an Intelligent Intrusion Detection and Prevention System against Web Application Malware

  • Jan 01, 2013
  • Ammar Alazab +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.