EVAGAN: Evasion Generative Adversarial Network for Low Data Regimes

09/14/2021
by   Rizwan Hamid Randhawa, et al.
0

A myriad of recent literary works has leveraged generative adversarial networks (GANs) to spawn 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 generating 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. Code will be available at https://github.com/rhr407/EVAGAN.

READ FULL TEXT

page 1

page 10

page 12

research
10/06/2022

Deep Reinforcement Learning based Evasion Generative Adversarial Network for Botnet Detection

Botnet detectors based on machine learning are potential targets for adv...
research
02/16/2022

Generative Adversarial Network-Driven Detection of Adversarial Tasks in Mobile Crowdsensing

Mobile Crowdsensing systems are vulnerable to various attacks as they bu...
research
11/01/2021

A Unified View of cGANs with and without Classifiers

Conditional Generative Adversarial Networks (cGANs) are implicit generat...
research
07/20/2022

Difficulty-Aware Simulator for Open Set Recognition

Open set recognition (OSR) assumes unknown instances appear out of the b...
research
11/01/2021

Rebooting ACGAN: Auxiliary Classifier GANs with Stable Training

Conditional Generative Adversarial Networks (cGAN) generate realistic im...
research
11/08/2020

Image Clustering using an Augmented Generative Adversarial Network and Information Maximization

Image clustering has recently attracted significant attention due to the...
research
10/29/2019

Adversarial Fisher Vectors for Unsupervised Representation Learning

We examine Generative Adversarial Networks (GANs) through the lens of de...

Please sign up or login with your details

Forgot password? Click here to reset