Multivariate calibration is an important tool for spectroscopic measurermnent of analyte con-centrations.We present a detailed study of a hybrid multivariate calibration technique,con-strained regularization(CR),and d...Multivariate calibration is an important tool for spectroscopic measurermnent of analyte con-centrations.We present a detailed study of a hybrid multivariate calibration technique,con-strained regularization(CR),and demonstrate its utility in noninvasive glucose sensing uasing Raman spectroscopy.Similar to partial least squares(PIS)and principal component regression(PCR),CR builds an implicit model and requires knowledge only of the concentrations of the analyte of interest.Calibration is treated as an inverse problem in which an optimal balance between model complexity and noise rejection is achieved.Prior information is included in the form of a spectroscopic constraint that can be obtained conveniently.When used with an appropriate constraint,CR provides a better calibration model compared to PLS in both numerical and experimental studies.展开更多
Transfer-based Adversarial Attacks(TAAs)can deceive a victim model even without prior knowledge.This is achieved by leveraging the property of adversarial examples.That is,when generated from a surrogate model,they re...Transfer-based Adversarial Attacks(TAAs)can deceive a victim model even without prior knowledge.This is achieved by leveraging the property of adversarial examples.That is,when generated from a surrogate model,they retain their features if applied to other models due to their good transferability.However,adversarial examples often exhibit overfitting,as they are tailored to exploit the particular architecture and feature representation of source models.Consequently,when attempting black-box transfer attacks on different target models,their effectiveness is decreased.To solve this problem,this study proposes an approach based on a Regularized Constrained Feature Layer(RCFL).The proposed method first uses regularization constraints to attenuate the initial examples of low-frequency components.Perturbations are then added to a pre-specified layer of the source model using the back-propagation technique,in order to modify the original adversarial examples.Afterward,a regularized loss function is used to enhance the black-box transferability between different target models.The proposed method is finally tested on the ImageNet,CIFAR-100,and Stanford Car datasets with various target models,The obtained results demonstrate that it achieves a significantly higher transfer-based adversarial attack success rate compared with baseline techniques.展开更多
基金funding from the National Science Foundation (NSF) CAREER Award (CBET1151154)the National Aeronautics and Space Administration (NASA)Early Career Faculty Grant (NNX12AQ44G)+2 种基金Gulf of Mexico Research Initiative (GoMRI-030)Cullen College of Engineering at the University of Houstonthe MIT Laser Biomedical Research Center supported by the NIH National Center for Research Resources,Grant No.P41-RR02594.
文摘Multivariate calibration is an important tool for spectroscopic measurermnent of analyte con-centrations.We present a detailed study of a hybrid multivariate calibration technique,con-strained regularization(CR),and demonstrate its utility in noninvasive glucose sensing uasing Raman spectroscopy.Similar to partial least squares(PIS)and principal component regression(PCR),CR builds an implicit model and requires knowledge only of the concentrations of the analyte of interest.Calibration is treated as an inverse problem in which an optimal balance between model complexity and noise rejection is achieved.Prior information is included in the form of a spectroscopic constraint that can be obtained conveniently.When used with an appropriate constraint,CR provides a better calibration model compared to PLS in both numerical and experimental studies.
基金supported by the Intelligent Policing Key Laboratory of Sichuan Province(No.ZNJW2022KFZD002)This work was supported by the Scientific and Technological Research Program of Chongqing Municipal Education Commission(Grant Nos.KJQN202302403,KJQN202303111).
文摘Transfer-based Adversarial Attacks(TAAs)can deceive a victim model even without prior knowledge.This is achieved by leveraging the property of adversarial examples.That is,when generated from a surrogate model,they retain their features if applied to other models due to their good transferability.However,adversarial examples often exhibit overfitting,as they are tailored to exploit the particular architecture and feature representation of source models.Consequently,when attempting black-box transfer attacks on different target models,their effectiveness is decreased.To solve this problem,this study proposes an approach based on a Regularized Constrained Feature Layer(RCFL).The proposed method first uses regularization constraints to attenuate the initial examples of low-frequency components.Perturbations are then added to a pre-specified layer of the source model using the back-propagation technique,in order to modify the original adversarial examples.Afterward,a regularized loss function is used to enhance the black-box transferability between different target models.The proposed method is finally tested on the ImageNet,CIFAR-100,and Stanford Car datasets with various target models,The obtained results demonstrate that it achieves a significantly higher transfer-based adversarial attack success rate compared with baseline techniques.
