TwinNet: A Double Sub-Network Framework for Detecting Universal Adversarial Perturbations

Yibin Ruan and Jiazhu Dai
Additional contact information
Yibin Ruan: School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China
Jiazhu Dai: School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China

Future Internet, 2018, vol. 10, issue 3, 1-13

Abstract: Deep neural network has achieved great progress on tasks involving complex abstract concepts. However, there exist adversarial perturbations, which are imperceptible to humans, which can tremendously undermine the performance of deep neural network classifiers. Moreover, universal adversarial perturbations can even fool classifiers on almost all examples with just a single perturbation vector. In this paper, we propose TwinNet, a framework for neural network classifiers to detect such adversarial perturbations. TwinNet makes no modification of the protected classifier. It detects adversarially perturbated examples by enhancing different types of features in dedicated networks and fusing the output of the networks later. The paper empirically shows that our framework can identify adversarial perturbations effectively with a slight loss in accuracy when predicting normal examples, which outperforms state-of-the-art works.

Keywords: deep neural network; universal adversarial perturbation; double sub-network; detecting; PCA; ImageNet (search for similar items in EconPapers)
JEL-codes: O3 (search for similar items in EconPapers)
Date: 2018
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1999-5903/10/3/26/pdf (application/pdf)
https://www.mdpi.com/1999-5903/10/3/26/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jftint:v:10:y:2018:i:3:p:26-:d:134935

Access Statistics for this article

Future Internet is currently edited by Ms. Grace You

More articles in Future Internet from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().