检索结果-内蒙古大学图书馆

LMP-GAN: Out-Of-Distribution Detection For Non-Control data Malware Attacks

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年 PP卷 PP页

作者： Wood, David Kapp, David Kebede, Temesgen Hirakawa, Keigo Wuhan University School of Computer Science China Wuhan University National Engineering Research Center for Multimedia Software Hubei Key Laboratory of Multimedia and Network Communication Engineering China Zhongguancun Academy China Wuhan University State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing China Sun Yat-sen University School of Geography and Planning China Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates Chongqing University College of Computer Science China The University of Tokyo Japan RIKEN Center for Advanced Intelligence Project Japan Intelligent Science & Technology Academy Limited CASIC China iFlytek Company Ltd. National Engineering Research Center of Speech and Language Information Processing China Nanyang Technological University College of Computing & Data Science Singapore Henan Academy of Sciences Aerospace Information Research Institute China

Anomaly detection is a common application of machine learning. Out-of-distribution (OOD) detection in particular is a semi-supervised anomaly detection technique where the detection method is trained only on the inlier (in-distribution) samples - unlike the fully supervised variant, the distribution of the outlier samples are never explicitly modeled in OOD detection tasks. In this work, we design a novel GAN-based OOD detection network specifically designed to protect a cyber-physical signal systems from novel Trojan malware called non-control data (NCD) attack that evades conventional malware detection techniques. Inspired in part by the classical locally most powerful (LMP) test in statistical inferences, the proposed LMP-GAN trains the OOD detector (discriminator) by generating OOD samples that are aimed at making maximal alteration to the inlier samples while evading detection. We experimentally compare the results to the state-of-the-art anomaly detection methods to demonstrate the benefits and the appropriateness of the LMP-GAN OOD detector. © 2025 IEEE.

关键词： Malware

来源：评论

学校读者我要写书评

暂无评论

Efficient quantum state transmission via perfect quantum network coding

引用

Science China(Information Sciences) 2019年第1期62卷 191-204页

作者： Zhen-Zhen LI Gang XU Xiu-Bo CHEN Zhiguo QU Xin-Xin NIU Yi-Xian YANG Information Security Center State Key Laboratory of Networking and Switching TechnologyBeijing University of Posts and Telecommunications Guizhou Provincial Key Laboratory of Public Big Data Guizhou University Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science and Technology

Quantum network coding with the assistance of auxiliary resources can achieve perfect transmission of the quantum state. This paper suggests a novel perfect network coding scheme to efficiently solve the quantum k-pair problem, in which only a few assisting resources are introduced. Specifically, only one pair of maximally entangled state needs to be pre-shared between two intermediate nodes, and only O(k) of classical information is transmitted though the network. Moreover, the classical communication used in our protocol does not cause transmission congestion, providing better adaptability to large-scale quantum k-pair *** relevant analyses and comparisons, we demonstrate that our proposed scheme saves resources and has good application value, thereby showing its high efficiency. Furthermore, the proposed scheme achieves 1-max flow quantum communication, and the achievable rate region result is extended from its counterpart over the butterfly network.

关键词： perfect quantum network coding quantum k-pair problem efficient quantum state transmission communication efficiency achievable rate region

来源：评论

学校读者我要写书评

暂无评论

Influence of Key Ecological Function Area Policy on the Components of Water Balance-A Case Study in Yangtze River Basin

SSRN

引用

SSRN 2025年

作者： You, Guangyong Xu, Yan Zhang, Minxia Gao, Yuanyun He, Honglin Zhang, Mengyu Liu, Bo Zhu, Minxin You, Juan Nanjing Institute of Environmental Sciences Ministry of Ecology and Environment Jiangsu Nanjing210042 China Jiangsu Frontier Electric Power Technology Company Limited Jiangsu Nanjing211102 China Key Laboratory of Ecosystem Network Observation and Modeling Institute of Geographic Sciences and Natural Resources Research Chinese Academy of Sciences Beijing100101 China National Ecosystem Science Data Center Beijing100101 China College of Resources and Environment University of Chinese Academy of Sciences Beijing100190 China School of Remote Sensing and Geomatics Engineering Nanjing University of Information Science and Technology Jiangsu Nanjing210044 China Hebei Engineering Consulting Institute Hebei Shijiazhuang050057 China

The National Key Ecological Function Area (KEFA) policy of China, the world's largest ecological compensation program, played an important role in improving the ecological functions. To reveal the effects of KEFA on land surface water balance components, this study analyzed the difference between KEFA area and the rest of the area (NKEF) in Yangtze River Basin (YRB). The results showed that, 1) the KEFA had higher interception loss (Ei) but lower actual evaporation (Ea) and transpiration (Et) than NKEF. The proportions of Ea, Et, Ei to precipitation (Pre) were higher in KEFA than NKEF, suggesting the KEFA had higher water consumption possibly resulting from the vegetation growth and dynamics. 2) Over the past decades, Ea, Et, and Ei, as well as their proportions to Precipitation (PRE), were significantly increased in YRB. A significant change point around the year 2000 coincided with the climate cycles periods and implementations of national ecological restoration programs i.e. National Grain for Green Program. 3) The long-term trends of Ea/Pre and the Ei/Pre were higher in KEFA than NKEF, especially for the post-2000 period. Compared with pre-2000 period, The Ea/Pre, Et/Pre of the NKEF in the post-2000 period displayed sharp decrease, suggesting the decreasing vegetation cover and water consumption. This study revealed the hydrological effects of KEFA policy, the findings are meaningful in evaluating and optimizing the KEFA policy. © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A UC-secure authenticated contributory group key exchange protocol based on discrete logarithm

A UC-secure authenticated contributory group key exchange pr...

引用

9th International Conference on Information Systems Security, ICISS 2013

作者： Sobhdel, Yasser Jalili, Rasool Data and Network Security Laboratory Department of Computer Engineering Sharif University of Technology Tehran Iran

ISBN: (纸本)9783642452031

Authenticated key exchange protocols allow parties to establish a common session key which in turn is fundamental to building secure channels. Authenticated group key exchange protocols allow parties to interact with each other and establish a common group session key and avoid peer to peer key exchange;in other words they pave the way to build a broadcast channel. We construct an authenticated group key exchange protocol over UC framework which has the contributiveness property;i.e., the output is not biased by inputs of any party. Our protocol uses CRS model and discrete logarithm. Other protocols over UC framework either are defined over RO model [19] or benefit from a non-standard hardness assumption [16]. © 2013 Springer-Verlag.

关键词： Uranium compounds

来源：评论

学校读者我要写书评

暂无评论

Privacy preservation based on full-domain generalization for incremental data publishing

引用

International Conference on Information Science and Applications, ICISA 2016

作者： Soontornphand, Torsak Harnsamut, Nattapon Natwichai, Juggapong Data Engineering and Network Technology Laboratory Department of Computer Engineering Chiang Mai University Chiang Mai Thailand

ISBN: (纸本)9789811005565

As data can be continuously collected and grow all the time with the enabling of advancement in IT infrastructure, the privacy protection mechanism which is designed for static data might not be able to cope with this situation effectively. In this paper, we present an incremental full-domain generalization based on k-anonymity model for incremental data publishing scenario. First, the characteristics of incremental data publishing for two releases is to be observed. Subsequently, we generalize the observation for the multiple data release problem. Then, we propose an effective algorithm to preserve the privacy of incremental data publishing. From the experiment results, our proposed approach is highly efficient as well as its effectiveness, privacy protection, is very close to the bruteforce algorithm generating the optimal solutions. © Springer Science+Business Media Singapore 2016.

关键词： data privacy

来源：评论

学校读者我要写书评

暂无评论

Prescribed Performance Control of One-DOF Link Manipulator With Uncertainties and Input Saturation Constraint

引用

IEEE/CAA Journal of Automatica Sinica 2019年第1期6卷 148-157页

作者： Yang Yang Jie Tan Dong Yue IEEE the College of Automation and the College of Artificial Intelligence Nanjing University of Posts and Telecommunications the Institute of Advanced Technology and Jiangsu Engineering Laboratory of Big Data Analysis and Control for Active Distribution Network Nanjing University of Posts and Telecommunications

In this paper, we mainly address the position control problem for one-degree of freedom(DOF) link manipulator despite uncertainties and the input saturation via the backstepping technique, active disturbance rejection control(ADRC) as well as predefined tracking performance functions. The extended state observer(ESO) is employed to compensate uncertain dynamics and disturbances, and it does not rely on the accurate model of systems. The tracking differentiator(TD) is utilized to substitute the derivative of the virtual control signals, and the explosion of complexity caused by repeated differentiations of nonlinear functions is removed. The auxiliary system is used to deal with the control input limitation, and the tracking accuracy and speed are improved by predefined tracking performance *** the help of the input-to-state stability(ISS) and Lyapunov stability theories, it is proven that the tracking error can be gradually converged into arbitrarily small neighborhood of the origin, and the tracking error is adjusted by suitable choice of control parameters. The simulation results are presented for the verification of the theoretical claims.

关键词： Active disturbance rejection control (ADRC) auxiliary system backstepping technique input saturation predefined tracking performance function

来源：评论

学校读者我要写书评

暂无评论

An Overview of General Theory of Security

引用

China Communications 2017年第7期14卷 1-10页

作者： Min Lei Yixian Yang Xinxin Niu Yu Yang Jie Hao Information Security Center Beijing University of Posts and Telecommunications Guizhou University Guizhou Provincial Key Laboratory of Public Big Data Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science & Technology

Cyber security lacks comprehensive theoretical guidance. General security theory, as a set of basic security theory concepts, is intended to guide cyber security and all the other security work. The general theory of security aims to unify the main branches of cyber security and establish a unified basic theory. This paper proposal an overview on the general theory of security, which is devoted to constructing a comprehensive model of network security. The hierarchical structure of the meridian-collateral tree is described. Shannon information theory is employed to build a cyberspace security model. Some central concepts of security, i.e., the attack and defense, are discussed and several general theorems on security are presented.

关键词： cyber security network attack and defense meridian-collateral theory

来源：评论

学校读者我要写书评

暂无评论

Distributed Tracking Control of a Class of Multi-agent Systems in Non-affine Pure-feedback Form Under a Directed Topology

引用

IEEE/CAA Journal of Automatica Sinica 2018年第1期5卷 169-180页

作者： Yang Yang Dong Yue College of Automation Nanjing University of Posts and Telecommunications Nanjing 210023 China Institute of Advanced Technology and Jiangsu Engineering Laboratory of Big Data Analysis and Control for Active Distribution Network Nanjing University of Posts and Telecommunications Nanjing 210023 China IEEE

In this paper, we consider a consensus tracking problem of a class of networked multi-agent systems(MASs)in non-affine pure-feedback form under a directed topology. A distributed adaptive tracking consensus control scheme is constructed recursively by the backstepping method, graph theory,neural networks(NNs) and the dynamic surface control(DSC)approach. The key advantage of the proposed control strategy is that, by the DSC technique, it avoids "explosion of complexity"problem along with the increase of the degree of individual agents and thus the computational burden of the scheme can be drastically reduced. Moreover, there is no requirement for prior knowledge about system parameters of individual agents and uncertain dynamics by employing NNs approximation *** then further show that, in theory, the designed control policy guarantees the consensus errors to be cooperatively semi-globally uniformly ultimately bounded(CSUUB). Finally, two examples are presented to validate the effectiveness of the proposed control strategy.

关键词： Backstepping consensus multi-agent systems(MASs) neural networks(NNs)

来源：评论

学校读者我要写书评

暂无评论

Event-trigger-based consensus secure control of linear multi-agent systems under DoS attacks over multiple transmission channels

引用

Science China(Information Sciences) 2020年第5期63卷 105-118页

作者： Yang YANG Yanfei LI Dong YUE College of Automation & College of Artificial Intelligence Nanjing University of Posts and Telecommunications Jiangsu Engineering Laboratory of Big Data Analysis and Control for Active Distribution Network Nanjing University of Posts and Telecommunications Institute of Advanced Technology Nanjing University of Posts and Telecommunications

This paper proposes a consensus secure control scheme in the presence of denial-of-service(DoS)attacks based on an event-trigger mechanism. In contrast to a scenario in which attacks are the same and simultaneously paralyze all channels, the DoS attack addressed in this paper occurs aperiodically and results in the independent interruption of multiple transmission channels. A sufficient condition for the attack duration is designed and a distributed event-triggered control scheme is proposed, where the updated instants are triggered aperiodically to reduce the required communication resources. It is shown that the overall system is stable with the proposed scheme according to the Lyapunov stability theory and that Zeno behavior is excluded. Finally, a numerical example is presented to verify the effectiveness of the proposed scheme.

关键词： multi-agent system event-triggered control consensus secure control denial-of-service attack multiple transmission channels

来源：评论

学校读者我要写书评

暂无评论

An aggregate flow based scheduler in multi-task cooperated UAVs network

引用

Chinese Journal of Aeronautics 2020年第11期33卷 2989-2998页

作者： Xiaohuan LI Ziqi XIE Jin YE Xin TANG Chunhai LI Fengzhu TANG Rong YU School of Information and Communication Guilin University of Electronic TechnologyGuilin 541004China Guangxi Key Laboratory of Multimedia Communications and Network Technology School of ComputerElectronics and InformationGuangxi UniversityNanning 530004China National Engineering Laboratory for Comprehensive Transportation Big Data Application Technology(Guangxi) Nanning 530001China School of Automation Guangdong University of TechnologyGuangzhou 510006China

Unmanned Aerial Vehicles(UAVs)cooperative multi-task system has become the research focus in recent ***,the existing network frameworks of UAVs are not flexible and efficient enough to deal with the complex multi-task scheduling,because they are not able to perceive the different *** this paper,a novel cooperated UAVs network framework for multi-task scheduling is *** is a three-layer network including a core layer,an aggregation layer and an execution layer,which enhances the efficiency of multi-task distribution,aggregation and ***,an Aggre Gate Flow(AGFlow)based scheduler is dedicatedly designed to maximize the task completion rate,whose key point is to aggregate flows belonging to one task during the multi-task transmission of UAVs network and to allocate priority by calculating the urgency-level of each *** results demonstrate that,compared with that of state-of-the-art scheduler,the average task completion rate of AGFlow based scheduler is raised by 0.278.

关键词： Mixed-flow scheduling Multi-task Task completion rate Unmanned Aerial Vehicles(UAVs) Urgency-level

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：