.png){kind=icon}
返回
Improving robustness with image filtering
.png){kind=icon}
OA
AI
DOI：10.1016/j.neucom.2024.127927.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Adversarial robustness is one of the most challenging problems in Deep Learning and Computer Vision research. State-of-the-art techniques to enforce robustness are based on Adversarial Training, a computationally costly optimization procedure. For this reason, many alternative solutions have been proposed, but none proved effective under stronger or adaptive attacks. This paper presents Image-Graph Extractor (IGE), a new image filtering scheme that extracts the fundamental nodes of an image and their connections through a graph structure. By utilizing the IGE representation, we have developed a new defense technique, Filtering as a Defense, which prevents attackers from creating malicious patterns that can deceive image classifiers. Moreover, we show that data augmentation with filtered images effectively improves the model's robustness to data corruptions. We validate our techniques on Convolutional Neural Networks on CIFAR-10, CIFAR-100, and ImageNet.
Keyword:
Robustness
Adversarial attacks and defenses
Adversarial training
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:
6.5
论文数:
2.5W
被引数:
6.5W
机构
.png){kind=icon}
