Effective and Robust Detection of Adversarial Examples via Benford-Fourier Coefficients

doi:10.1007/s11633-022-1328-1

CASIA OpenIR > 学术期刊 > Machine Intelligence Research

	Effective and Robust Detection of Adversarial Examples via Benford-Fourier Coefficients
	Cheng-Cheng Ma1,2 ; Bao-Yuan Wu 3,4; Yan-Bo Fan5 ; Yong Zhang 5; Zhi-Feng Li 5
发表期刊	Machine Intelligence Research
ISSN	2731-538X
	2023
卷号	20 期号:5 页码:666-682
摘要	Adversarial example has been well known as a serious threat to deep neural networks (DNNs). In this work, we study the detection of adversarial examples based on the assumption that the output and internal responses of one DNN model for both adversarial and benign examples follow the generalized Gaussian distribution (GGD) but with different parameters (i.e., shape factor, mean, and variance). GGD is a general distribution family that covers many popular distributions (e.g., Laplacian, Gaussian, or uniform). Therefore, it is more likely to approximate the intrinsic distributions of internal responses than any specific distribution. Besides, since the shape factor is more robust to different databases rather than the other two parameters, we propose to construct discriminative features via the shape factor for adversarial detection, employing the magnitude of Benford-Fourier (MBF) coefficients, which can be easily estimated using responses. Finally, a support vector machine is trained as an adversarial detector leveraging the MBF features. Extensive experiments in terms of image classification demonstrate that the proposed detector is much more effective and robust in detecting adversarial examples of different crafting methods and sources compared to state-of-the-art adversarial detection methods.
关键词	Adversarial defense, adversarial detection, generalized Gaussian distribution, Benford-Fourier coefficients, image classification
DOI	10.1007/s11633-022-1328-1
引用统计	被引频次：1[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/56002
专题	学术期刊_Machine Intelligence Research
作者单位	1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China 2.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China 3.School of Data Science, The Chinese University of Hong Kong, Shenzhen 518172, China 4.Shenzhen Research Institute of Big Data, Shenzhen 518172, China 5.AI Lab, Tencent Inc., Shenzhen 518057, China
第一作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Cheng-Cheng Ma,Bao-Yuan Wu,Yan-Bo Fan,et al. Effective and Robust Detection of Adversarial Examples via Benford-Fourier Coefficients[J]. Machine Intelligence Research,2023,20(5):666-682.
APA	Cheng-Cheng Ma,Bao-Yuan Wu,Yan-Bo Fan,Yong Zhang,& Zhi-Feng Li.(2023).Effective and Robust Detection of Adversarial Examples via Benford-Fourier Coefficients.Machine Intelligence Research,20(5),666-682.
MLA	Cheng-Cheng Ma,et al."Effective and Robust Detection of Adversarial Examples via Benford-Fourier Coefficients".Machine Intelligence Research 20.5(2023):666-682.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
MIR-2021-12-305.pdf（9598KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载