Black-box adversarial machine learning attack on network traffic classification

Muhammad Usama, Adnan Qayyum, Junaid Qadir, Ala Al-Fuqaha

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

38 Citations (Scopus)

Abstract

Deep machine learning techniques have shown promising results in network traffic classification, however, the robustness of these techniques under adversarial threats is still in question. Deep machine learning models are found vulnerable to small carefully crafted adversarial perturbations posing a major question on the performance of deep machine learning techniques. In this paper, we propose a black-box adversarial attack on network traffic classification. The proposed attack successfully evades deep machine learning-based classifiers which highlights the potential security threat of using deep machine learning techniques to realize autonomous networks.

Original languageEnglish
Title of host publication2019 15th International Wireless Communications and Mobile Computing Conference, IWCMC 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages84-89
Number of pages6
ISBN (Electronic)9781538677476
DOIs
Publication statusPublished - Jun 2019
Event15th IEEE International Wireless Communications and Mobile Computing Conference, IWCMC 2019 - Tangier, Morocco
Duration: 24 Jun 201928 Jun 2019

Publication series

Name2019 15th International Wireless Communications and Mobile Computing Conference, IWCMC 2019

Conference

Conference15th IEEE International Wireless Communications and Mobile Computing Conference, IWCMC 2019
Country/TerritoryMorocco
CityTangier
Period24/06/1928/06/19

Keywords

  • Adversarial machine learning
  • Black-box adversarial attack
  • Network traffic classification

Fingerprint

Dive into the research topics of 'Black-box adversarial machine learning attack on network traffic classification'. Together they form a unique fingerprint.

Cite this