paper-with-me

홈 › Papers

Visually Imperceptible Adversarial Patch Attacks on Digital Images

2020-12-02 · Yaguan Qian, Jiamin Wang, Bin Wang, Shaoning Zeng, Zhaoquan Gu, Shouling Ji, Wassim Swaileh

The vulnerability of deep neural networks (DNNs) to adversarial examples has attracted more attention. Many algorithms have been proposed to craft powerful adversarial examples. However, most of these algorithms modified the global or local region of pixels without taking network explanations into account. Hence, the perturbations are redundant, which are easily detected by human eyes. In this paper, we propose a novel method to generate local region perturbations. The main idea is to find a contributing feature region (CFR) of an image by simulating the human attention mechanism and then add perturbations to CFR. Furthermore, a soft mask matrix is designed on the basis of an activation map to finely represent the contributions of each pixel in CFR. With this soft mask, we develop a new loss function with inverse temperature to search for optimal perturbations in CFR. Due to the network explanations, the perturbations added to CFR are more effective than those added to other regions. Extensive experiments conducted on CIFAR-10 and ILSVRC2012 demonstrate the effectiveness of the proposed method, including attack success rate, imperceptibility, and transferability.

📄 PDF Abstract BibTeX arXiv:2012.00909

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Towards Physical, Imperceptible Adversarial Attacks via Adversarial Programs

2021-09-29 · Itai Mesery, Dana Drachsler Cohen

Adversarial examples were originally defined as imperceptible perturbations which cause a deep neural network to misclassify. However, the majority of imperceptible perturbation attacks require to perturb a large number …

Program Synthesis

Robustness Out of the Box: Compositional Representations Naturally Defend Against Black-Box Patch Attacks

2020-12-01 · Christian Cosgrove, Adam Kortylewski, Chenglin Yang, Alan Yuille

Patch-based adversarial attacks introduce a perceptible but localized change to the input that induces misclassification. While progress has been made in defending against imperceptible attacks, it remains unclear how pa…

Traffic Sign Recognition

Adversarial Vulnerability of Temporal Feature Networks for Object Detection

2022-08-23 · Svetlana Pavlitskaya, Nikolai Polley, Michael Weber, J. Marius Zöllner

Taking into account information across the temporal domain helps to improve environment perception in autonomous driving. However, it has not been studied so far whether temporally fused neural networks are vulnerable to…

Autonomous DrivingObjectobject-detectionObject Detection

Robust Synthesis of Adversarial Visual Examples Using a Deep Image Prior

2019-07-03 · Thomas Gittings, Steve Schneider, John Collomosse

We present a novel method for generating robust adversarial image examples building upon the recent `deep image prior' (DIP) that exploits convolutional network architectures to enforce plausible texture in image synthes…

Image Generation

Imperceptible Jailbreaking against Large Language Models

2025-10-06 · Kuofeng Gao, Yiming Li, Chao Du, Xin Wang 외 arxiv

Jailbreaking attacks on the vision modality typically rely on imperceptible adversarial perturbations, whereas attacks on the textual modality are generally assumed to require visible modifications (e.g., non-semantic su…