Preprocessing Network Traffic using Topological Data Analysis for Data Poisoning Detection

dc.contributor.authorMonkam, Galamo F.
dc.contributor.authorDe Lucia, Michael J.
dc.contributor.authorBastian, Nathaniel D.
dc.date.accessioned2023-12-19T13:32:13Z
dc.date.available2023-12-19T13:32:13Z
dc.date.issued2023-11-07
dc.description.abstractThe rise of cyber attacks has prompted researchers to develop innovative techniques for detecting malicious activities to improve network security. Data poisoning attacks present a unique challenge when training machine learning (ML) models for the detection of malicious activity within network traffic. Traditional techniques for identifying such data poisoning attacks often lack efficiency when applied to network traffic. In this paper, we propose a novel approach that combines Topological Data Analysis (TDA) with unsupervised learning for preprocessing network traffic, aiming to improve data poisoning detection. TDA enables the capture of complex topological properties and underlying patterns in data sets, which we hypothesize can aid in identifying subtle adversarial modifications within network data. By leveraging TDA combined with an unsupervised learning algorithm, our proposed method can effectively detect poisoned data, enabling developers to remove it before training a MLbased model for network intrusion detection. This work opens up new avenues for research in network security and highlights the potential of TDA for pre-processing network traffic data.
dc.description.sponsorshipArmy Cyber Institute
dc.identifier.citationG. F. Monkam, M. J. D. Lucia and N. D. Bastian, "Preprocessing Network Traffic using Topological Data Analysis for Data Poisoning Detection," 2023 IEEE Conference on Dependable and Secure Computing (DSC), Tampa, FL, USA, 2023, pp. 1-8, doi: 10.1109/DSC61021.2023.10354143.
dc.identifier.doihttps://doi.org/10.1109/DSC61021.2023.10354143
dc.identifier.urihttps://hdl.handle.net/20.500.14216/1464
dc.publisherIEEE
dc.relation.ispartof2023 IEEE Conference on Dependable and Secure Computing (DSC)
dc.subjectTraining
dc.subjectData analysis
dc.subjectScalability
dc.subjectNetwork Intrusion Detection
dc.subjectTelecommunication traffic
dc.subjectNetwork Security
dc.subjectData models
dc.titlePreprocessing Network Traffic using Topological Data Analysis for Data Poisoning Detection
dc.typeproceedings-article
local.peerReviewedYes

Files