Evasion Generative Adversarial Network for Low Data Regimes

Nauman Aslam, Rizwan Hamid Randhawa*, Mohammad Alauthman, Husnain Rafiq

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)
97 Downloads (Pure)

Abstract

A myriad of recent literary works have leveraged generative adversarial networks (GANs) to generate unseen evasion samples. The purpose is to annex the generated data with the original train set for adversarial training to improve the detection performance of machine learning (ML) classifiers. The quality of generated adversarial samples relies on the adequacy of training data samples. However, in low data regimes like medical diagnostic imaging and cybersecurity, the anomaly samples are scarce in number. This paper proposes a novel GAN design called evasion generative adversarial network (EVAGAN) that is more suitable for low data regime problems that use oversampling for detection improvement of ML classifiers. EVAGAN not only can generate evasion samples but its discriminator can act as an evasion-aware classifier. We have considered auxiliary classifier GAN (ACGAN) as a benchmark to evaluate the performance of EVAGAN on cybersecurity (ISCX-2014, CIC-2017, and CIC2018) botnet and computer vision (MNIST) datasets. We demonstrate that EVAGAN outperforms ACGAN for unbalanced datasets with respect to detection performance, training stability, and time complexity. EVAGAN's generator quickly learns to generate the low sample class and hardens its discriminator simultaneously. In contrast to ML classifiers that require security hardening after being adversarially trained by GAN-generated data, EVAGAN renders it needless. The experimental analysis proves that EVAGAN is an efficient evasion hardened model for low data regimes for the selected cybersecurity and computer vision datasets.
Original languageEnglish
Pages (from-to)1076-1088
Number of pages13
JournalIEEE Transactions on Artificial Intelligence
Volume4
Issue number5
Early online date4 Aug 2022
DOIs
Publication statusPublished - 1 Oct 2023

Fingerprint

Dive into the research topics of 'Evasion Generative Adversarial Network for Low Data Regimes'. Together they form a unique fingerprint.

Cite this