GaDoT: GAN-based Adversarial Training for Robust DDoS Attack Detection

Maged Abdelaty*, Sandra Scott-Hayward, Roberto Doriguzzi-Corin, Domenico Siracusa

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

21 Citations (Scopus)
290 Downloads (Pure)

Abstract

Machine Learning (ML) has proven to be effective in many application domains. However, ML methods can be vulnerable to adversarial attacks, in which an attacker tries to fool the classification/prediction mechanism by crafting the input data. In the case of ML-based Network Intrusion Detection Systems (NIDSs), the attacker might use their knowledge of the intrusion detection logic to generate malicious traffic that remains undetected. One way to solve this issue is to adopt adversarial training, in which the training set is augmented with adversarial traffic samples. This paper presents an adversarial training approach called GADoT, which leverages a Generative Adversarial Network (GAN) to generate adversarial DDoS samples for training. We show that a state-of-the-art NIDS with high accuracy on popular datasets can experience more than 60% undetected malicious flows under adversarial attacks. We then demonstrate how this score drops to 1.8% or less after adversarial training using GADoT.
Original languageEnglish
Title of host publicationNinth IEEE Conference on Communications and Network Security (IEEE CNS 2021): Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
DOIs
Publication statusPublished - 10 Feb 2022
EventIEEE Conference on Communications and Network Security - Virtual
Duration: 04 Oct 202106 Oct 2021
https://cns2021.ieee-cns.org/

Conference

ConferenceIEEE Conference on Communications and Network Security
Period04/10/202106/10/2021
Internet address

Fingerprint

Dive into the research topics of 'GaDoT: GAN-based Adversarial Training for Robust DDoS Attack Detection'. Together they form a unique fingerprint.
  • Securing AI-based Security Systems

    Scott-Hayward, S., 01 Jun 2022, GCSP Strategic Security Analysis, 25.

    Research output: Contribution to specialist publicationArticle

    Open Access
    File

Cite this