supported by the National Natural Science Foundation of China(Grant Nos.U20B2049,U21B2018 and 62302344).
Adversarial training has been widely considered the most effective defense against adversarial attacks.However,recent studies have demonstrated that a large discrepancy exists in the class-wise robustness of adversari...
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).
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...
This work reviews models and methods for determining the dynamic response of pavements to moving vehicle loads in the framework of continuum-based three dimensional models and linear theories.This review emphasizes th...
Models based on MLP-Mixer architecture are becoming popular,but they still sufer from adversarial examples.Although it has been shown that MLP-Mixer is more robust to adversarial attacks compared to convolutional neur...
The emergence of adversarial examples has revealed the inadequacies in the robustness of image classification models based on Convolutional Neural Networks (CNNs). Particularly in recent years, the discovery of natura...
This study represents a pioneering effort to analyze the impact of avalanches descending into Morskie Oko from Marchwiczny Gully,the most active avalanche path around the lake.It focuses on catastrophic avalanches tha...
Supported by the National Natural Science Foundation of China(U1903214,62372339,62371350,61876135);the Ministry of Education Industry University Cooperative Education Project(202102246004,220800006041043,202002142012);the Fundamental Research Funds for the Central Universities(2042023kf1033)。
Recent years have witnessed the ever-increasing performance of Deep Neural Networks(DNNs)in computer vision tasks.However,researchers have identified a potential vulnerability:carefully crafted adversarial examples ca...
As cities worldwide face increasing energy demands and environmental sustainability challenges,the need for innovative solutions becomes more urgent.Smart cities,driven by advances in Artificial Intelligence(AI),offer...
National Natural Science Foundation of China(No.11671207).
This paper studies silted algebras,namely,endomorphism algebras of 2-term silting complexes,over path algebras of Dynkin quivers.We describe an algorithm to produce all basic 2-term silting complexes over the path alg...
The National Natural Science Foundation of China (61876001);Opening Foundation of State Key Laboratory of Cognitive Intelligence,Opening Foundation of State Key Laboratory of Cognitive Intelligence(iED2022-006);Scientific Research Planning Project of Anhui Province (2022AH050072)
Attackers inject the designed adversarial sample into the target recommendation system to achieve illegal goals,seriously affecting the security and reliability of the recommendation system.It is difficult for attacke...