检索结果-内蒙古大学图书馆

Unveiling the Superiority of Unsupervised Learning on GPU Cryptojacking Detection: Practice on Magnetic Side Channel-Based Mechanism

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 4874-4889页

作者： Cao, Hangcheng Xu, Guowen He, Ziyang Shi, Shaoqing Xu, Shengmin Wu, Cong Ning, Jianting Hunan University College of Computer Science and Electronic Engineering Changsha410012 China City University of Hong Kong Department of Computer Science Hong Kong Hong Kong University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu610054 China Zhengzhou University School of Cyber Science and Engineering Zhengzhou450001 China Zhengzhou University International College Zhengzhou450001 China Fujian Provincial Key Laboratory of Network Security and Cryptology College of Computer and Cyber Security Fuzhou350007 China Nanyang Technological University College of Computing and Data Science Jurong West 639798 Singapore Wuhan University School of Cyber Science and Engineering Wuhan430072 China City University of Macau Faculty of Data Science Macau China

Ample profits of GPU cryptojacking attract hackers to recklessly invade victims’ devices, for completing specific cryptocurrency mining tasks. Such malicious invasion undoubtedly obstructs normal device usage and wastes computation resources. To resist the threat of GPU cryptojacking, existing works aim to timely detect and clear away it, by distinguishing the dissimilitude between it and legitimate applications. However, these detection mechanisms inappropriately rely on two conflict cornerstones, manifested in leveraging mutable samples of illegitimate cryptojacking to design supervision-based detection models requiring samples with stable patterns. This limitation compromises the practicability of existing detection mechanisms in the face of mutable cryptojacking samples. To fill the gap, we explore the superiority of unsupervised learning in handling this issue and further propose an unsupervised manner-enabled detection mechanism named MagInspector, only using legitimate applications’ magnetic signatures from GPU side channels for model construction. MagInspector innovates in training an unsupervised autoencoder network by an adversarial mode that well learns the stable signature patterns of legitimate applications, while incompatible with mutable cryptojacking ones. In the process of model training, we elaborately extract mutual energy cumulation distribution features to represent legitimate applications to overcome the impact of their inter-type differences. Meanwhile, a locality sensitive hashing-driven outlier removal algorithm is designed to enhance MagInspector’s robustness to the noise samples. Finally, extensive experiments are conducted on GPUs covering four generations of common NVIDIA architectures and two generations of AMD architectures;the results show that applying MagInspector to mutable cryptojacking signature detection achieves a significant average accuracy improvement of 25.5% and 17.8%, respectively. © 2005-2012 IEEE.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Reliability-driven real-time task replication for fault tolerance in hierarchical scheduling multiprocessor systems

Reliability-driven real-time task replication for fault tole...

引用

IET International Conference on Information and Communications Technologies, IETICT 2013

作者： Liu, Lin Li, Renfa Li, Rui Xie, Yong Zeng, Qingguang Key Laboratory for Embedded and Network Computing of Hunan Province Hunan University Changsha China

ISBN: (纸本)9781849196536

The increasing complexity of systems poses a big challenge to design systems with fault-tolerant capability. The aim of this study was to establish fault-tolerant system for multiprocessor platform with the help of hierarchical scheduling framework. A mathematical fault and reliability model for hierarchical scheduling framework was proposed firstly, and then a heuristic algorithm by exploiting the difference of task resource overhead and the probability of task failures was presented and a task replication scheme was given lastly. The experimental results demonstrated the proposed scheme could effectively guarantee reliability goal and reduce resource consumption simultaneously.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

Optimized roles set algorithm in distributed parallel computing system

Optimized roles set algorithm in distributed parallel comput...

引用

26th International Conference on Parallel Computational Fluid Dynamics, ParCFD 2013

作者： Wu, Wenkang Tang, Zhuo Key Laboratory for Embedded and Network Computing of Hunan Province Changsha Hunan 410082 China

ISBN: (纸本)9783642539619

With the rapid development of computer technology, distributed computing and parallel computing have made great progress. Distributed parallel computing system is a combination of distributed computing and parallel computing, which can provide fast solutions to information sharing and subtasks in high-speed network environment. In this paper, we propose a new access control model-Distributed Parallel computing Role Based Access Control (DPCRBAC) Model on the basis of the traditional RBAC model. We propose a new roles set assignment algorithm-Optimized Roles Set (ORS) algorithm. According to the results of simulation, the proposed algorithm ORS can effectively improve the efficiency roles and is effective in reducing role conflicts in the process of role assignment, and ensure the safety and reliability of the distributed parallel computing system. © Springer-Verlag Berlin Heidelberg 2014.

关键词： Distributed computer systems

来源：评论

学校读者我要写书评

暂无评论

Delay-derivative-dependent Stability Conditions for Uncertain T-S Fuzzy Systems with Interval Time-varying Delay

Delay-derivative-dependent Stability Conditions for Uncertai...

引用

第三十二届中国控制会议

作者： AN Ji-yao XIA Xian-zhong LI Ren-fa College of Information Science and Engineering Hunan University Key Laboratory of Embedded and Network Computing of Hunan Province Hunan University

ISBN: (纸本)9781479900305

This paper considers the problem of stability analysis of uncertain T-S fuzzy systems with interval time-varying delay. The system uncertainties are assumed to be time-varying and *** new delay-derivative-dependent stability conditions are derived by constructing a novel delay-dependent Lyapunov-Krasovskii functional and estimating a tighter upper bound of its time derivative without ignoring some useful terms and involving any direct *** proposed approach leads to some less conservative LMI conditions as shown through some numerical examples.

关键词： Uncertain systems T-S fuzzy systems Stability Lyapunov-Krasovskii Functional(LKF) LMI

来源：评论

学校读者我要写书评

暂无评论

An Efficient Three-Factor Privacy-Preserving Authentication and key Agreement Protocol for Vehicular Ad-Hoc network

引用

China Communications 2021年第12期18卷 315-331页

作者： Tao Xu Cheng Xu Zisang Xu School of Electronic Engineering Beijing University of Posts and TelecommunicationsBeijing 100876China Key Laboratory for Embedded and Network Computing of Hunan Province Changsha 410082China

As an indispensable part of the Intelli-gent Transportation System(ITS),the vehicular ad-hoc network(VANET)has attracted widespread atten-tion from academia and *** order to ensure the security of VANET,vehicles need to be authen-ticated before accessing the *** existing authentication protocols in VANET adopt the Trusted Authority(TA)with centralized structure which is re-sponsible for the authentication tasks of all ***,the large-scale network consume a lot of computing resources,which leads to unacceptable de-lay in message transmission in *** reducing the computational cost of TA,an efficient three-factor privacy-preserving authentication and key agreement protocol was proposed in our *** from before,the RoadSide Unit(RSU)no longer acts as an intermediate node but is responsible for assisting user authentication,which lead to the computational cost of TA is very *** formal and informal analysis,our protocol demonstrates excellent ***-pared with previous studies,our work emerges advan-tages and superiorities in the following aspects:com-putational cost,communication cost,security proper-ties and functions,message loss ratio,and message *** data and evidence indicate that our protocol is an ideal choice for large-scale VANET.

关键词： authentication vehicular ad-hoc network security three-factor

来源：评论

学校读者我要写书评

暂无评论

An offline scheduling algorithm for certifiable mixed-critical embedded system

An offline scheduling algorithm for certifiable mixed-critic...

引用

26th International Conference on Parallel Computational Fluid Dynamics, ParCFD 2013

作者： Wu, Chengtao Li, Renfa Key Laboratory for Embedded and Network Computing of Hunan Province Changsha 410086 China

ISBN: (纸本)9783642539619

In modern embedded platforms, safety-critical functionalities that must be certified correctly to high level of assurance co-exist with less critical software that are not subjected to certification requirements. These caused many scheduling problems. Nowadays, many researches focused on promising techniques for meeting the following two goals: (1) being able to certify the safety-critical functionalities under very conservative assumptions, and (2) ensuring high utilization of platform resources under less pessimistic assumptions. In this paper we propose an offline scheduling algorithm called OSS for certifiable mixed-criticality systems on a uniprocessor platform. Compared to previous proposed algorithm CBEDF, OSS can supply better schedulability. © Springer-Verlag Berlin Heidelberg 2014.

关键词： Scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

The implementation of MapReduce scheduling algorithm based on priority

The implementation of MapReduce scheduling algorithm based o...

引用

26th International Conference on Parallel Computational Fluid Dynamics, ParCFD 2013

作者： Gu, Lianjun Tang, Zhuo Xie, Guoqi Key Laboratory for Embedded and Network Computing of Hunan Province Changsha 410082 China

ISBN: (纸本)9783642539619

Nowadays cloud computing has become a popular platform for scientific applications. Cloud computing intends to share a large scale resources and equipments of computation, storage, information and knowledge for scientific researches. Job Scheduling problem is a core and challenging research issue in the current cloud computation area, and the aim is to the reasonable control of the job execution sequence as well as the allocation of computing resources, making the job total completion time of the shortest and resources are fully utilized. Data locality is one of the main factors to influence scheduling algorithm. The paper proposed an improved scheduling algorithm based on priority, after taking full account of data locality (IPDSA), which can distinguish the user's job levels, so as to reduce the job execution time and avoid losing into locally optimal solution. The experimental results on the Hadoop platform show that the new scheduling algorithm can reduce the job average execution time, and raises the rate availability of resources. © Springer-Verlag Berlin Heidelberg 2014.

关键词： MapReduce

来源：评论

学校读者我要写书评

暂无评论

Dynamic slack reclamation with EDL scheduling for periodic multimode real-time task

Dynamic slack reclamation with EDL scheduling for periodic m...

引用

26th International Conference on Parallel Computational Fluid Dynamics, ParCFD 2013

作者： Hu, Huan Li, Renfa Key Laboratory for Embedded and Network Computing of Hunan Province Changsha 410086 China

ISBN: (纸本)9783642539619

The multiframe task has been considered in dynamic real-time scheduling, its different execution mode optional feature can handle the resource waste caused by pessimistic estimation of the execution requirement. But in runtime, the selection of an instance execution mode with more execution requirement may cause a deadline miss. In this paper, we propose a slack reclamation mechanism of configuring an appropriate execution mode under deadline guarantee. This mechanism is composed of offline phase and online phase. In offline, the initial execution mode of task instances is selected and the static slack is calculated. In online, on the basis of EDL scheduling list, mode upgrade list and actual execution requirement of the instance, the slack is assigned to the instance with the highest value of the r/R in Slack available zone. Our simulation shows that this scheme can obtain a better result of the accured reward when the task's BCET is greater than 40% of its WCET. © Springer-Verlag Berlin Heidelberg 2014.

关键词： Scheduling

来源：评论

学校读者我要写书评

暂无评论

Personalized News Recommendation Based on the Text and Image Integration

引用

Computers, Materials & Continua 2020年第7期64卷 557-570页

作者： Kehua Yang Shaosong Long Wei Zhang Jiqing Yao Jing Liu College of Computer Science and Electronic Engineering and Key Laboratory for Embedded and Network Computing of Hunan Province Hunan UniversityChangsha410082China Oath Verizon Company New York10007USA

The personalized news recommendation has been very popular in the news recommendation *** most research,the picture information in the news is ignored,but the information conveyed to the users through pictures is more intuitive and more likely to affect the users’reading interests than the one in the textual ***,in this paper,a model that combines images and texts in the news is *** this model,the new tags are extracted from the images and texts in the news,and based on these new tags,an adaptive tag(AT)algorithm is *** AT algorithm selects the tags the user is interested in based on the user *** particular,the AT algorithm can predict tags that a user may be interested in with the help of the tag correlation graph without any user *** proposed AT algorithm is verified by *** experimental results verified the AT algorithm regarding three evaluation indexes F1-score(F1),area under curve(AUC)and mean reciprocal rank(MRR).The recommended effect of the proposed algorithm is found to be better than those of the various baseline algorithms on real-world datasets.

关键词： News recommendation F1 AUC MRR feedback correlation graph

来源：评论

学校读者我要写书评

暂无评论

Multi-Label Learning Based on Transfer Learning and Label Correlation

引用

Computers, Materials & Continua 2019年第7期61卷 155-169页

作者： Kehua Yang Chaowei She Wei Zhang Jiqing Yao Shaosong Long College of Computer Science and Electronic Engineering and Key Laboratory for Embedded and Network Computing of Hunan Province Hunan UniversityChangsha410082China Oath Verizon Company ManhattanNew York10007USA

In recent years,multi-label learning has received a lot of ***,most of the existing methods only consider global label correlation or local label *** fact,on the one hand,both global and local label correlations can appear in real-world situation at same *** the other hand,we should not be limited to pairwise labels while ignoring the high-order label *** this paper,we propose a novel and effective method called GLLCBN for multi-label ***,we obtain the global label correlation by exploiting label semantic ***,we analyze the pairwise labels in the label space of the data set to acquire the local ***,we build the original version of the label dependency model by global and local label *** that,we use graph theory,probability theory and Bayesian networks to eliminate redundant dependency structure in the initial version model,so as to get the optimal label dependent ***,we obtain the feature extraction model by adjusting the Inception V3 model of convolution neural network and combine it with the GLLCBN model to achieve the multi-label *** experimental results show that our proposed model has better performance than other multi-label learning methods in performance evaluating.

关键词： Bayesian networks multi-label learning global and local label correlations transfer learning

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：