检索结果-内蒙古大学图书馆

Generating Adversarial Patterns in Facial Recognition with Visual Camouflage

Journal of Shanghai Jiaotong University (science) 2024年 1-12页

作者： Bao, Qirui Mei, Haiyang Wei, Huilin Lü, Zheng Wang, Yuxin Yang, Xin Key Laboratory of Social Computing and Cognitive Intelligence of Ministry of Education School of Control Science and EngineeringSchool of Computer Science and Technology Dalian University of Technology Liaoning Dalian116024 China Systems Engineering Institute Academy of Military Sciences Beijing100141 China

Deep neural networks, especially face recognition models, have been shown to be vulnerable to adversarial examples. However, existing attack methods for face recognition systems either cannot attack black-box models, are not universal, have cumbersome deployment processes, or lack camouflage and are easily detected by the human eye. In this paper, we propose an adversarial pattern generation method for face recognition and achieve universal black-box attacks by pasting the pattern on the frame of goggles. To achieve visual camouflage, we use a generative adversarial network (GAN). The scale of the generative network of GAN is increased to balance the performance conflict between concealment and adversarial behavior, the perceptual loss function based on VGG19 is used to constrain the color style and enhance GAN’s learning ability, and the fine-grained meta-learning adversarial attack strategy is used to carry out black-box attacks. Sufficient visualization results demonstrate that compared with existing methods, the proposed method can generate samples with camouflage and adversarial characteristics. Meanwhile, extensive quantitative experiments show that the generated samples have a high attack success rate against black-box models. © 2023, Shanghai Jiao Tong University.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Generalizability of Memorization Neural Networks 38

Generalizability of Memorization Neural Networks

引用

38th Conference on Neural Information Processing systems, NeurIPS 2024

作者： Yu, Lijia Gao, Xiao-Shan Zhang, Lijun Miao, Yibo State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences China Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

The neural network memorization problem is to study the expressive power of neural networks to interpolate a finite dataset. Although memorization is widely believed to have a close relationship with the strong generalizability of deep learning when using over-parameterized models, to the best of our knowledge, there exists no theoretical study on the generalizability of memorization neural networks. In this paper, we give the first theoretical analysis of this topic. Since using i.i.d. training data is a necessary condition for a learning algorithm to be generalizable, memorization and its generalization theory for i.i.d. datasets are developed under mild conditions on the data distribution. First, algorithms are given to construct memorization networks for an i.i.d. dataset, which have the smallest number of parameters and even a constant number of parameters. Second, we show that, in order for the memorization networks to be generalizable, the width of the network must be at least equal to the dimension of the data, which implies that the existing memorization networks with an optimal number of parameters are not generalizable. Third, a lower bound for the sample complexity of general memorization algorithms and the exact sample complexity for memorization algorithms with constant number of parameters are given. It is also shown that there exist data distributions such that, to be generalizable for them, the memorization network must have an exponential number of parameters in the data dimension. Finally, an efficient and generalizable memorization algorithm is given when the number of training samples is greater than the efficient memorization sample complexity of the data distribution. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Impacts of gravitational-wave background from supermassive black hole binaries on the detection of compact binaries by LISA

引用

Chinese Physics C 2024年第6期48卷 198-203页

作者：黄帆毕研晨曹周键黄庆国 CAS Key Laboratory of Theoretical Physics Institute of Theoretical PhysicsChinese Academy of SciencesBeijing 100190China School of Physical Sciences University of Chinese Academy of SciencesBeijing 100049China Institute of Applied Mathematics Academy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China School of Fundamental Physics and Mathematical Sciences Hangzhou Institute for Advanced StudyUCASHangzhou 310024China

In the frequency band of the Laser Interferometer Space Antenna(LISA),extensive research has been conducted on the impact of foreground confusion noise generated by galactic binaries within the Milky Way ***,recent evidence of a stochastic signal,announced by the NANOGrav,EPTA,PPTA,CPTA,and InPTA,indicates that the stochastic gravitational-wave background(SGWB)generated by supermassive black hole binaries(SMBHBs)can contribute strong background noise within the LISA *** the presence of such strong noise,it is expected to have significant impacts on LISA's scientific *** this study,we investigate the impacts of the SGWB generated by SMBHBs on the detection of individual massive black hole binaries,verified galactic binaries,and extreme mass ratio inspirals in the context of *** find it essential to resolve and eliminate the excess noise from the SGWB to guarantee the success of LISA's missions.

关键词： gravitational-wave background supermassive black hole binaries LISA

来源：评论

学校读者我要写书评

暂无评论

A practical PID variable stiffness control and its enhancement for compliant force-tracking interactions with unknown environments

引用

science China(Technological sciences) 2023年第10期66卷 2882-2896页

作者： ZHANG Xin ZHOU Hao LIU JinGuo JU ZhaoJie LENG YuQuan YANG ChenGuang State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of SciencesShenyang 110016China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of SciencesShenyang 110169China University of Chinese Academy of Sciences Beijing 100049China School of Computing University of PortsmouthPortsmouth PO13HEUK Shenzhen Key Laboratory of Biomimetic Robotics and Intelligent Systems Department of Mechanical and Energy EngineeringSouthern University of Science and TechnologyShenzhen 518055China Key Laboratory of Autonomous Systems and Networked Control College of Automation Science and EngineeringSouth China University of TechnologyGuangzhou 510640China

Compliant interaction control is a key technology for robots performing contact-rich manipulation *** design of the compliant controller needs to consider the robot hardware because complex control algorithms may not be compatible with the hardware performance,especially for some industrial robots with low bandwidth *** paper focuses on effective and easy-to-use compliant control algorithms for position/velocity-controlled *** by human arm stiffness adaptation behavior,a novel variable target stiffness(NVTS)admittance control strategy is proposed for adaptive force tracking,in which a proportional integral derivative(PID)variable stiffness law is designed to update the stiffness coefficient of the admittance function by the force and position ***,its stability and force-tracking capability are theoretically *** addition,an impact compensator(Impc)is integrated into the NVTS controller to enhance its disturbance-suppression capability when the robot is subjected to strong vibration disturbances in complicated surface polishing *** proposed controllers are validated through four groups of experimental tests using different robots and the corresponding results demonstrate that they have high-accuracy tracking capability and strong adaptability in unknown environments.

关键词： compliant interaction control force tracking PID variable stiffness impact compensator unknown environments

来源：评论

学校读者我要写书评

暂无评论

Geometry Flow-Based Deep Riemannian Metric Learning

引用

IEEE/CAA Journal of Automatica Sinica 2023年第9期10卷 1882-1892页

作者： Yangyang Li Chaoqun Fei Chuanqing Wang Hongming Shan Ruqian Lu Key Lab of MADIS Academy of Mathematics and Systems Science Chinese Academy of SciencesBeijing 100190China IEEE Institute of Science and Technology for Brain-Inspired Intelligence and Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence(Ministry of Education)and MOE Frontiers Center for Brain Science Fudan UniversityShanghai 200433 Shanghai Center for Brain Science and Brain-Inspired Technology Shanghai 200031China

Deep metric learning(DML)has achieved great results on visual understanding tasks by seamlessly integrating conventional metric learning with deep neural *** deep metric learning methods focus on designing pair-based distance loss to decrease intra-class distance while increasing interclass ***,these methods fail to preserve the geometric structure of data in the embedding space,which leads to the spatial structure shift across mini-batches and may slow down the convergence of embedding *** alleviate these issues,by assuming that the input data is embedded in a lower-dimensional sub-manifold,we propose a novel deep Riemannian metric learning(DRML)framework that exploits the non-Euclidean geometric structural *** that the curvature information of data measures how much the Riemannian(nonEuclidean)metric deviates from the Euclidean metric,we leverage geometry flow,which is called a geometric evolution equation,to characterize the relation between the Riemannian metric and its *** DRML not only regularizes the local neighborhoods connection of the embeddings at the hidden layer but also adapts the embeddings to preserve the geometric structure of the *** several benchmark datasets,the proposed DRML outperforms all existing methods and these results demonstrate its effectiveness.

关键词： Curvature regularization deep metric learning(DML) embedding learning geometry flow riemannian metric

来源：评论

学校读者我要写书评

暂无评论

Decomposing Visual and Semantic Correlations for Both Fully Supervised and Few-Shot Image Classification

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第4期5卷 1658-1668页

作者： Zhang, Chunjie Zheng, Xiaolong Beijing Jiaotong University Institute of Information Science Beijing100044 China Beijing Jiaotong University Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China University of Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems The State of Key Laboratory of Management and Control for Complex System Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence Beijing100190 China

Most image classification methods are designed to either boost the classification accuracies with abundant supervision, or cope with the shortage of supervision information. This is often achieved by using the visual and semantic information of other sources. However, these methods use the visual and semantic information within the same class independently, leaving their intrinsic correlations unconsidered. Objects and disturbing components as well as noise exist on the same image. Besides, semantic representations also contain noisy information. To solve the problems mentioned above, we propose a novel method for both fully supervised image classification and few-shot image classification by decomposing visual and semantic correlations. We jointly explore the intrinsic correlations of visual and semantic information of images within the same class. For each class, we decompose its visual and semantic correlations using low-rank and sparse constraint respectively. The decomposed low-rank parts character the intrinsic correlations of images can be used in a linear transformation way. Using the decomposed parts of each class, Classification can be achieved by reconstruction error minimization. We conduct experiments on several datasets for both fully supervised image classification and few-shot image classification. Experimental results well show the effectiveness of the proposed method. © 2020 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Testing for Error Correlation in Semi-Functional Linear Models

引用

Journal of systems science & Complexity 2023年第4期36卷 1697-1716页

作者： YANG Bin CHEN Min ZHOU Jianjun Yunnan Key Laboratory of Statistical Modeling and Data Analysis Yunnan UniversityKunming 650091China City College Kunming University of Science and TechnologyKunming 650051China School of Mathematical Sciences Shanxi UniversityTaiyuan 030006China Academy of Mathematics and Systems Science Chinese Academy of SciencesBeijing 100190China

Existing methods for analyzing semi-functional linear models usually assumed that random errors are not serially correlated or serially correlated with the known ***,in some applications,these assumptions on random errors may be unreasonable or *** this end,this paper aims at testing error correlation in a semi-functional linear model(SFLM).Based on the empirical likelihood approach,the authors construct an empirical likelihood ratio statistic to test the serial correlation of random errors and identify the order of autocorrelation if the serial correlation *** proposed test statistic does not need to estimate the variance as it is data adaptive and possesses the nonparametric version of Wilks'*** studies are conducted to investigate the performance of the proposed test *** real examples are illustrated by the proposed test method.

关键词： Empirical likelihood error correlation functional principal component analysis semifunctional linear model spline estimation Wilks'theorem

来源：评论

学校读者我要写书评

暂无评论

MMH-FE:AMulti-Precision and Multi-Sourced Heterogeneous Privacy-Preserving Neural Network Training Based on Functional Encryption

引用

Computers, Materials & Continua 2025年第3期82卷 5387-5405页

作者： Hao Li Kuan Shao Xin Wang Mufeng Wang Zhenyong Zhang The State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang550025China Key Laboratory of Computing Power Network and Information Security Ministry of EducationShandong Computer Science CenterQilu University of Technology(Shandong Academy of Sciences)Jinan250014China China Industrial Control Systems Cyber Emergency Response Team Beijing100040China

Due to the development of cloud computing and machine learning,users can upload their data to the cloud for machine learning model ***,dishonest clouds may infer user data,resulting in user data *** schemes have achieved secure outsourced computing,but they suffer from low computational accuracy,difficult-to-handle heterogeneous distribution of data from multiple sources,and high computational cost,which result in extremely poor user experience and expensive cloud computing *** address the above problems,we propose amulti-precision,multi-sourced,andmulti-key outsourcing neural network training ***,we design a multi-precision functional encryption computation based on Euclidean ***,we design the outsourcing model training algorithm based on a multi-precision functional encryption with multi-sourced ***,we conduct experiments on three *** results indicate that our framework achieves an accuracy improvement of 6%to 30%.Additionally,it offers a memory space optimization of 1.0×2^(24) times compared to the previous best approach.

关键词： Functional encryption multi-sourced heterogeneous data privacy preservation neural networks

来源：评论

学校读者我要写书评

暂无评论

Turán Numbers of Expanded Intersecting Cliques in 3-graphs

引用

Journal of the Operations Research Society of China 2024年第4期12卷 952-964页

作者： Yu-Cong Tang Tong Li Gui-Ying Yan School of Mathematics Nanjing University of Aeronautics and AstronauticsNanjing211106JiangsuChina Key Laboratory of Mathematical Modelling and High Performance Computing of Air Vehicles(NUAA) Ministry of Industry and Information TechnologyNanjing211106JiangsuChina School of Mathematical Sciences Academy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing100190China University of Chinese Academy of Sciences Beijing100049China

Let l>r≥*** a 2-graph F,the expansion E^((r))of F is an r-graph obtained from F by adding r-2 new vertices into each *** F is a clique of order l,the Turán number ex(n,F^((r)))was first asymptotically determined by Mubayi(J Comb Theory Ser B 96:122–134,2006)and exactly computed by Pikhurko(J Comb Theory Ser B 103:220–225,2013).Let F_(k,l)be the 2-graph on(l-1)k+1 vertices consisting of k cliques of order l intersecting at exactly one *** determine the exact Turán number ex(n,F_(k,l)^((3)))for all l>3,k≥1,and sufficiently large n,as well as the corresponding extremal graphs.

关键词： Expansion Turán number 3-Graph Intersecting cliques Stability

来源：评论

学校读者我要写书评

暂无评论

Periodicity in Hedge-myopic system and an asymmetric NE-solving paradigm for two-player zero-sum games

arXiv

引用

arXiv 2024年

作者： Guo, Xinxiang Mu, Yifen Yang, Xiaoguang School of Mathematical Sciences University of Chinese Academy of Sciences China The Key Laboratory of Systems and Control Institute of Systems Science Academy of Mathematics and Systems Science Chinese Academy of Sciences China Key Laboratory of Management Decision and Information System Institute of Systems Science Academy of Mathematics and Systems Science Chinese Academy of Sciences China

In this paper, we consider the n×n two-payer zero-sum repeated game in which one player (player X) employs the popular Hedge (also called multiplicative weights update) learning algorithm while the other player (player Y) adopts the myopic best response. We investigate the dynamics of such Hedge-myopic system by defining a metric Q(xt), which measures the distance between the stage strategy xt and Nash Equilibrium (NE) strategy of player X. We analyze the trend of Q(xt) and prove that it is bounded and can only take finite values on the evolutionary path when the payoff matrix is rational and the game has an interior NE. Based on this, we prove that the stage strategy sequence of both players are periodic after finite stages and the time-averaged strategy of player Y within one period is an exact NE strategy. Accordingly, we propose an asymmetric paradigm for solving two-player zero-sum games. For the special game with rational payoff matrix and an interior NE, the paradigm can output the precise NE strategy;for any general games we prove that the time-averaged strategy can converge to an approximate NE. In comparison to the NE-solving method via Hedge self-play, this HBR paradigm exhibits faster computation/convergence,better stability and can attain precise NE convergence in most real *** Codes 91A05, 91A25, 91A68 Copyright © 2024, The Authors. All rights reserved.

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：