.png){kind=icon}
返回
Detecting adversarial examples using image reconstruction differences
.png){kind=icon}
PRE
AI
DOI：10.1007/s00500-023-07961-z.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The adversarial examples (AEs) cause misjudgments and damage the robustness of the DNNs systems. Previous studies have defended against AEs by detecting, but it is challenging to ensure a stable and high performance of detecting AEs, while with a poor false detection. To this end, an AEs detection method named image reconstruction differences (IRD) is proposed to enhance the robustness of DNNs. Firstly, we use an end-to-end Com-Rec network to reconstruct examples with feature compression to expand the distinguishing features. Secondly, propose an image reconstruction differences based on information-theoretic VIF, structural information UQI and spectral information RASE composition to discriminate AEs. Moreover, we introduce the idea of integrated learning to form a strong random forest binary classifier to enhance the performance of detecting AEs. We further validate it through extensive experiments on the MNIST and CIFAR-10 datasets. These experiments demonstrated that the IRD effectively detected AEs and achieved a high average accuracy of 98.33%. Specifically it also performs favorably against the following methods based on Feature Squeezing, Local Intrinsic Dimensionality, Kernel Density and Network Invariance Checking with an average detection rate of 99.54% and a 1.44% average false positive rate.
Keyword:
Deep neural networks
Adversarial examples
Detection
Compress and reconstruct
Image reconstruction differences
Random forest
期刊
IF:
2.5
论文数:
1.0W
被引数:
2.1W
机构
暂无机构信息
引用论文
First definitive observations of meteor shower particles using a high-power large-aperture radar.png)
Icarus
IcarusIF0
PREAI
分享收藏Adversarial example detection for DNN models: a review and experimental comparisonDNN模型的对抗性示例检测: 回顾和实验比较
PREAI
分享收藏Uncertainty estimation for stereo matching based on evidential deep learning基于证据深度学习的立体匹配不确定性估计PATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏分享收藏The Early Cambrian Mianyang-Changning Intracratonic Sag and Its Control on Petroleum Accumulation in the Sichuan Basin, ChinaGeofluidsOAAI
GeofluidsIF0
OAAI分享收藏
查看更多内容