ManiGen: A Manifold Aided Black-Box Generator of Adversarial Examples
Open Access
- 7 October 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 197086-197096
Abstract
From recent research work, it has been shown that neural network (NN) classifiers are vulnerable to adversarial examples which contain special perturbations that are ignored by human eyes while can mislead NN classifiers. In this paper, we propose a practical black-box adversarial example generator, dubbed ManiGen. ManiGen does not require any knowledge of the inner state of the target classifier. It generates adversarial examples by searching along the manifold, which is a concise representation of input data. Through extensive set of experiments on different datasets, we show that (1) adversarial examples generated by ManiGen can mislead standalone classifiers by being as successful as the state-of-the-art white-box generator, Carlini, and (2) adversarial examples generated by ManiGen can more effectively attack classifiers with state-of-theart defenses.Keywords
All Related Versions
Funding Information
- Deputyship for Research and Innovation Ministry of Education in Saudi Arabia (1120)
This publication has 9 references indexed in Scilit:
- GanDef: A GAN Based Adversarial Training Defense for Neural Network Classifier2019
- ZK-GanDef: A GAN Based Zero Knowledge Adversarial Training Defense for Neural Networks2019
- Using Intuition from Empirical Properties to Simplify Adversarial Training Defense2019
- ZOO2017
- MagNet2017
- Towards Evaluating the Robustness of Neural Networks2017
- Practical Black-Box Attacks against Machine Learning2017
- Automatically Evading Classifiers: A Case Study on PDF Malware Classifiers2016
- ImageNet: A large-scale hierarchical image database2009