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

doi:10.1007/s11633-022-1328-1

CORC > 自动化研究所 > 中国科学院自动化研究所 > 学术期刊 > International Journal of Automation and Computing

	Effective and Robust Detection of Adversarial Examples via Benford-Fourier Coefficients
	Cheng-Cheng Ma 4,5
刊名	Machine Intelligence Research
	2023
卷号	20 期号:5 页码:666-682
关键词	Adversarial defense, adversarial detection, generalized Gaussian distribution, Benford-Fourier coefficients, image classification
ISSN号	2731-538X
DOI	10.1007/s11633-022-1328-1
英文摘要	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.
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/52443]
专题	自动化研究所_学术期刊_International Journal of Automation and Computing
作者单位	1.AI Lab, Tencent Inc., Shenzhen 518057, China 2.Shenzhen Research Institute of Big Data, Shenzhen 518172, China 3.School of Data Science, The Chinese University of Hong Kong, Shenzhen 518172, China 4.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China 5.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
推荐引用方式 GB/T 7714	Cheng-Cheng Ma. Effective and Robust Detection of Adversarial Examples via Benford-Fourier Coefficients[J]. Machine Intelligence Research,2023,20(5):666-682.
APA	Cheng-Cheng Ma.(2023).Effective and Robust Detection of Adversarial Examples via Benford-Fourier Coefficients.Machine Intelligence Research,20(5),666-682.
MLA	Cheng-Cheng Ma."Effective and Robust Detection of Adversarial Examples via Benford-Fourier Coefficients".Machine Intelligence Research 20.5(2023):666-682.