DDSG-GAN: Generative Adversarial Network with Dual Discriminators and Single Generator for Black-Box Attacks

Fangwei Wang, Zerou Ma, Xiaohan Zhang, Qingru Li () and Changguang Wang ()
Additional contact information
Fangwei Wang: Key Laboratory of Network and Information Security of Hebei Province, College of Computer & Cyber Security, Hebei Normal University, Shijiazhuang 050024, China
Zerou Ma: Key Laboratory of Network and Information Security of Hebei Province, College of Computer & Cyber Security, Hebei Normal University, Shijiazhuang 050024, China
Xiaohan Zhang: Key Laboratory of Network and Information Security of Hebei Province, College of Computer & Cyber Security, Hebei Normal University, Shijiazhuang 050024, China
Qingru Li: Key Laboratory of Network and Information Security of Hebei Province, College of Computer & Cyber Security, Hebei Normal University, Shijiazhuang 050024, China
Changguang Wang: Key Laboratory of Network and Information Security of Hebei Province, College of Computer & Cyber Security, Hebei Normal University, Shijiazhuang 050024, China

Mathematics, 2023, vol. 11, issue 4, 1-18

Abstract: As one of the top ten security threats faced by artificial intelligence, the adversarial attack has caused scholars to think deeply from theory to practice. However, in the black-box attack scenario, how to raise the visual quality of an adversarial example (AE) and perform a more efficient query should be further explored. This study aims to use the architecture of GAN combined with the model-stealing attack to train surrogate models and generate high-quality AE. This study proposes an image AE generation method based on the generative adversarial networks with dual discriminators and a single generator (DDSG-GAN) and designs the corresponding loss function for each model. The generator can generate adversarial perturbation, and two discriminators constrain the perturbation, respectively, to ensure the visual quality and attack effect of the generated AE. We extensively experiment on MNIST, CIFAR10, and Tiny-ImageNet datasets. The experimental results illustrate that our method can effectively use query feedback to generate an AE, which significantly reduces the number of queries on the target model and can implement effective attacks.

Keywords: artificial intelligence; security threat; adversarial attacks; adversarial examples; generative adversarial networks (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/11/4/1016/pdf (application/pdf)
https://www.mdpi.com/2227-7390/11/4/1016/ (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:jmathe:v:11:y:2023:i:4:p:1016-:d:1070793

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

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