Structure Invariant Transformation for better Adversarial Transferability Article Swipe

MAKE IMPACT

Xiaosen Wang , Zeliang Zhang , Jianping Zhang · YOU? · · 2023 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2309.14700

Given the severe vulnerability of Deep Neural Networks (DNNs) against adversarial examples, there is an urgent need for an effective adversarial attack to identify the deficiencies of DNNs in security-sensitive applications. As one of the prevalent black-box adversarial attacks, the existing transfer-based attacks still cannot achieve comparable performance with the white-box attacks. Among these, input transformation based attacks have shown remarkable effectiveness in boosting transferability. In this work, we find that the existing input transformation based attacks transform the input image globally, resulting in limited diversity of the transformed images. We postulate that the more diverse transformed images result in better transferability. Thus, we investigate how to locally apply various transformations onto the input image to improve such diversity while preserving the structure of image. To this end, we propose a novel input transformation based attack, called Structure Invariant Attack (SIA), which applies a random image transformation onto each image block to craft a set of diverse images for gradient calculation. Extensive experiments on the standard ImageNet dataset demonstrate that SIA exhibits much better transferability than the existing SOTA input transformation based attacks on CNN-based and transformer-based models, showing its generality and superiority in boosting transferability. Code is available at https://github.com/xiaosen-wang/SIT.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2309.14700

PDF

https://arxiv.org/pdf/2309.14700

OA Status

green

Cited By

5

Related Works

10

OpenAlex ID

https://openalex.org/W4387148101

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4387148101

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2309.14700

Digital Object Identifier

Title

Structure Invariant Transformation for better Adversarial Transferability

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2023

Year of publication

Publication date

2023-09-26

Full publication date if available

Authors

Xiaosen Wang, Zeliang Zhang, Jianping Zhang

List of authors in order

Landing page

https://arxiv.org/abs/2309.14700

Publisher landing page

PDF URL

https://arxiv.org/pdf/2309.14700

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2309.14700

Direct OA link when available

Concepts

Transferability, Computer science, Adversarial system, Generality, Transformation (genetics), Artificial intelligence, Invariant (physics), Pattern recognition (psychology), Machine learning, Mathematics, Psychotherapist, Psychology, Mathematical physics, Gene, Chemistry, Logit, Biochemistry

Top concepts (fields/topics) attached by OpenAlex

Cited by

5

Total citation count in OpenAlex

Citations by year (recent)

2025: 3, 2024: 1, 2023: 1

Per-year citation counts (last 5 years)

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload