Home // ICIMP 2021, The Sixteenth International Conference on Internet Monitoring and Protection // View article

SIGMA: Strengthening IDS with GAN and Metaheuristics Attacks

Authors:
Simon Msika
Alejandro Quintero
Foutse Khomh

Keywords: Cybersecurity; IDS; Deep Learning; Machine Learn- ing; GAN; Metaheuristics

Abstract:
An Intrusion Detection System (IDS) is a key cybersecurity tool for network administrators as it identifies malicious traffic and cyberattacks. With the recent successes of machine learning techniques like deep learning, more and more IDS are now using machine learning algorithms to detect attacks faster. However, these systems lack robustness when facing previously unseen types of attacks. This work explores the possibility of leveraging generative adversarial models to improve the robustness of machine learning based IDS. More specifically, we generate adversarial examples, iteratively, and uses it to retrain a machine learning-based IDS, until a convergence of the detection rate. A round of improvement consists of a generative phase, in which we use GANs and metaheuristics to generate instances; an evaluation phase in which we calculate the detection rate of those newly generated attacks; and a training phase, in which we train the IDS with those attacks. We have evaluated the SIGMA method for four standard machine learning classification algorithms acting as IDS, with a combination of GAN and a hybrid local-search and genetic algorithm, to generate new datasets of attacks. Our results show that SIGMA can suc- cessfully generate adversarial attacks against different machine learning based IDS. Also, using SIGMA, we can improve the performance of an IDS to up to 100% after as little as two rounds of improvement

Pages: 10 to 20

Copyright: Copyright (c) IARIA, 2021

Publication date: May 30, 2021

Published in: conference

ISSN: 2308-3980

ISBN: 978-1-61208-862-4

Location: Valencia, Spain

Dates: from May 30, 2021 to June 3, 2021