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
For improving the translation quality of transfer-based MT system,a new metric for rule evaluation was proposed and applied to rule-base optimization.At the same time,a frequency filter was used to delete redundance b...For improving the translation quality of transfer-based MT system,a new metric for rule evaluation was proposed and applied to rule-base optimization.At the same time,a frequency filter was used to delete redundance before new acquired rules were added into rule-base.The new optimization method was applied to a general MT system.Experimental results show that the frequency filter is helpful to provide the knowledge expansion space of MT system for new acquired rules.The translation assessment score of open test corpus (including 2500 Chinese sentences) obtained is increased by 3.58% under 5-gram Nist metric,which is two times of that obtained by previous methods.展开更多
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.
基金Sponsored by the High Technology Research and Development Program of China (Grant No.2002AA117010-09)the National Natural Science Foun-dation of China (Grant No. 60375019)
文摘For improving the translation quality of transfer-based MT system,a new metric for rule evaluation was proposed and applied to rule-base optimization.At the same time,a frequency filter was used to delete redundance before new acquired rules were added into rule-base.The new optimization method was applied to a general MT system.Experimental results show that the frequency filter is helpful to provide the knowledge expansion space of MT system for new acquired rules.The translation assessment score of open test corpus (including 2500 Chinese sentences) obtained is increased by 3.58% under 5-gram Nist metric,which is two times of that obtained by previous methods.
