EXAMPLES

作品数:262被引量:223H指数:7
导出分析报告
相关作者:李笛甄霖曹晓昌俞建王小玲更多>>
相关机构:西安外国语大学黑龙江大学上海交通大学华东师范大学更多>>
相关期刊:更多>>
相关基金:国家自然科学基金国家社会科学基金中国博士后科学基金国家重点基础研究发展计划更多>>
-

检索结果分析

结果分析中...
条 记 录,以下是1-10
视图:
排序:
Fairness is essential for robustness:fair adversarial training by identifying and augmenting hard examples
《Frontiers of Computer Science》2025年第3期1-13,共13页Ningping MOU Xinli YUE Lingchen ZHAO Qian WANG 
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...
关键词:robust fairness adversarial training hard example data augmentation 
Enhancing Adversarial Example Transferability via Regularized Constrained Feature Layer
《Computers, Materials & Continua》2025年第4期157-175,共19页Xiaoyin Yi Long Chen Jiacheng Huang Ning Yu Qian Huang 
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...
关键词:Adversarial examples black-box transferability regularized constrained transfer-based adversarial attacks 
Models and methods for dynamic response of 3D flexible and rigid pavements to moving loads:A review by representative examples
《Journal of Road Engineering》2025年第1期65-91,共27页Edmond V.Muho Niki D.Beskou Jiang Qian 
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...
关键词:Flexible pavements Rigid(concrete)pavements Moving vehicle loads Three dimensional models LINEARITY Dynamic response 
Maxwell’s Demon in MLP-Mixer:towards transferable adversarial attacks
《Cybersecurity》2025年第1期180-188,共9页Haoran Lyu Yajie Wang Yu‑an Tan Huipeng Zhou Yuhang Zhao Quanxin Zhang 
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...
关键词:Adversarial attacks Adversarial examples Image classifcation 
Exploratory Research on Defense against Natural Adversarial Examples in Image Classification
《Computers, Materials & Continua》2025年第2期1947-1968,共22页Yaoxuan Zhu Hua Yang Bin Zhu 
Corresponding Author:Bin Zhu.Email:zhubin@nudt.edu.cn。
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...
关键词:Image classification convolutional neural network natural adversarial example data set defense against adversarial examples 
Examples and effects of avalanches on the surface of mountain lakes:Morskie Oko,a case study from Poland(Tatra Mountains)
《Journal of Mountain Science》2025年第2期375-390,共16页Adam CHOIŃSKI Wojciech DENEGA Andrzej MACIAS Witold PINIARSKI 
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...
关键词:Snow avalanches Mountain lakes SEDIMENTATION Morskie Oko Tatra Mountains Avalanche modeling 
A Survey of Adversarial Examples in Computer Vision:Attack,Defense,and Beyond
《Wuhan University Journal of Natural Sciences》2025年第1期1-20,共20页XU Keyizhi LU Yajuan WANG Zhongyuan LIANG Chao 
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...
关键词:computer vision adversarial examples adversarial attack adversarial defense 
Leveraging AI for Energy-Efficient Smart Cities: Architectural and Urban Planning Solutions for Sustainable Growth - A Comparative Case Study of Amman City and International Examples
《Journal of Civil Engineering and Architecture》2024年第12期620-632,共13页Mohmd Addad Shehadeh Al-Taani 
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...
关键词:Artificial intelligence smart cities energy efficiency urban planning sustainable architecture. 
Some Examples of Silted Algebras of Dynkin Type
《Algebra Colloquium》2024年第4期575-594,共20页Ruoyun Xing 
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...
关键词:silted algebra tilted algebra 2-term silting complex strictly shod algebra 
Black⁃box adversarial attacks with imperceptible fake user profiles for recommender systems
《南京大学学报(自然科学版)》2024年第6期881-899,共19页Qian Fulan Liu Jinggang Chen Hai Chen Wenbin Zhao Shu Zhang Yanping 
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...
关键词:recommendation systems adversarial examples transferability imperceptible 
检索报告 对象比较 聚类工具 使用帮助 返回顶部