paper-with-me

홈 › Papers

Vision Transformers: the threat of realistic adversarial patches

2025-09-25 · Kasper Cools, Clara Maathuis, Alexander M. van Oers, Claudia S. Hübner, Nikos Deligiannis, Marijke Vandewal, Geert De Cubber arxiv

The increasing reliance on machine learning systems has made their security a critical concern. Evasion attacks enable adversaries to manipulate the decision-making processes of AI systems, potentially causing security breaches or misclassification of targets. Vision Transformers (ViTs) have gained significant traction in modern machine learning due to increased 1) performance compared to Convolutional Neural Networks (CNNs) and 2) robustness against adversarial perturbations. However, ViTs remain vulnerable to evasion attacks, particularly to adversarial patches, unique patterns designed to manipulate AI classification systems. These vulnerabilities are investigated by designing realistic adversarial patches to cause misclassification in person vs. non-person classification tasks using the Creases Transformation (CT) technique, which adds subtle geometric distortions similar to those occurring naturally when wearing clothing. This study investigates the transferability of adversarial attack techniques used in CNNs when applied to ViT classification models. Experimental evaluation across four fine-tuned ViT models on a binary person classification task reveals significant vulnerability variations: attack success rates ranged from 40.04% (google/vit-base-patch16-224-in21k) to 99.97% (facebook/dino-vitb16), with google/vit-base-patch16-224 achieving 66.40% and facebook/dinov3-vitb16 reaching 65.17%. These results confirm the cross-architectural transferability of adversarial patches from CNNs to ViTs, with pre-training dataset scale and methodology strongly influencing model resilience to adversarial attacks.

📄 PDF Abstract BibTeX arXiv:2509.21084

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Attack

Similar Papers 제목 키워드 기반

On the interplay of adversarial robustness and architecture components: patches, convolution and attention

2022-09-14 · Francesco Croce, Matthias Hein

In recent years novel architecture components for image classification have been developed, starting with attention and patches used in transformers. While prior works have analyzed the influence of some aspects of archi…

Adversarial Robustnessimage-classificationImage Classification

Generating Visually Realistic Adversarial Patch

2023-12-05 · Xiaosen Wang, Kunyu Wang

Deep neural networks (DNNs) are vulnerable to various types of adversarial examples, bringing huge threats to security-critical applications. Among these, adversarial patches have drawn increasing attention due to their …

Position

Are Vision Transformers Robust to Patch-wise Perturbations?

2021-09-29 · Jindong Gu, Volker Tresp, Yao Qin

The recent advances in Vision Transformer (ViT) have demonstrated its impressive performance in image classification, which makes it a promising alternative to Convolutional Neural Network (CNN). Unlike CNNs, ViT represe…

image-classificationImage Classification

When Adversarial Training Meets Vision Transformers: Recipes from Training to Architecture

2022-10-14 · Yichuan Mo, Dongxian Wu, Yifei Wang, Yiwen Guo 외

Vision Transformers (ViTs) have recently achieved competitive performance in broad vision tasks. Unfortunately, on popular threat models, naturally trained ViTs are shown to provide no more adversarial robustness than co…

Adversarial Robustness

Random Position Adversarial Patch for Vision Transformers

2023-07-09 · Mingzhen Shao

Previous studies have shown the vulnerability of vision transformers to adversarial patches, but these studies all rely on a critical assumption: the attack patches must be perfectly aligned with the patches used for lin…

Position