.png){kind=icon}
返回
One-index vector quantization based adversarial attack on image classification
.png){kind=icon}
OA
AI
DOI：10.1016/j.patrec.2024.09.001.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
To improve storage and transmission, images are generally compressed. Vector quantization (VQ) is a popular compression method as it has a high compression ratio that suppresses other compression techniques. Despite this, existing adversarial attack methods on image classification are mostly performed in the pixel domain with few exceptions in the compressed domain, making them less applicable in real-world scenarios. In this paper, we propose a novel one-index attack method in the VQ domain to generate adversarial images by a differential evolution algorithm, successfully resulting in image misclassification in victim models. The one-index attack method modifies a single index in the compressed data stream so that the decompressed image is misclassified. It only needs to modify a single VQ index to realize an attack, which limits the number of perturbed indexes. The proposed method belongs to a semi-black-box attack, which is more in line with the actual attack scenario. We apply our method to attack three popular image classification models, i.e., Resnet, NIN, and VGG16. On average, 55.9 % and 77.4 % of the images in CIFAR-10 and Fashion MNIST, respectively, are successfully attacked, with a high level of misclassification confidence and a low level of image perturbation.
Keyword:
Adversarial attack
Image classification
Vector quantization
Deep Neural Networks
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.3
论文数:
8.0K
被引数:
1.6W
机构
引用论文
New fuzzy solution for determining anticipation and evaluation behavior during car-following maneuvers.png)
Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering
Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile EngineeringIF0
PREAI
分享收藏分享收藏分享收藏Hormone-Inducible Expression and Metal Affinity Chromatography of Recombinant Proteins in Saccharomyces cerevisiae激素诱导表达与金属亲和层析技术在酿酒酵母中的重组蛋白研究
PREAI
分享收藏Joint fingerprinting and decryption with noise-resistant for vector quantization imagesSIGNAL PROCESSING
SIGNAL PROCESSINGIF3.6
PREAI
分享收藏
查看更多内容