Enhancing the Transferability of Adversarial Examples with Feature Transformation

Hao-Qi Xu, Cong Hu () and He-Feng Yin
Additional contact information
Hao-Qi Xu: School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214122, China
Cong Hu: School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214122, China
He-Feng Yin: School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214122, China

Mathematics, 2022, vol. 10, issue 16, 1-14

Abstract: The transferability of adversarial examples allows the attacker to fool deep neural networks (DNNs) without knowing any information about the target models. The current input transformation-based method generates adversarial examples by transforming the image in the input space, which implicitly integrates a set of models by concatenating image transformation into the trained model. However, the input transformation-based methods ignore the manifold embedding and hardly extract intrinsic information from high-dimensional data. To this end, we propose a novel feature transformation-based method (FTM), which conducts feature transformation in the feature space. FTM can improve the robustness of adversarial example by transforming the features of data. Combining with FTM, the intrinsic features of adversarial examples are extracted to generate transferable adversarial examples. The experimental results on two benchmark datasets show that FTM could effectively improve the attack success rate (ASR) of the state-of-the-art (SOTA) methods. FTM improves the attack success rate of the Scale-Invariant Method on Inception_v3 from 62.6% to 75.1% on ImageNet, which is a large margin of 12.5%.

Keywords: adversarial example; feature transformation; black-box attack; ensemble attack; deep neural network (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.mdpi.com/2227-7390/10/16/2976/pdf (application/pdf)
https://www.mdpi.com/2227-7390/10/16/2976/ (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:10:y:2022:i:16:p:2976-:d:891228

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 ().