检索结果-内蒙古大学图书馆

IEEE International Conference on data Mining (ICDM)

作者： Yuecen Wei Xingcheng Fu Qingyun Sun Hao Peng Jia Wu Jinyan Wang Xianxian Li Guangxi Key Lab of Multi-source Information Mining & Security Guangxi Normal University Guilin China School of Computer Science and Engineering Guangxi Normal University Guilin China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China School of Computing Macquarie University Sydney Australia

Social networks are considered to be heterogeneous graph neural networks (HGNNs) with deep learning technological advances. HGNNs, compared to homogeneous data, absorb various aspects of information about individuals in the training stage. That means more information has been covered in the learning result, especially sensitive information. However, the privacy-preserving methods on homogeneous graphs only preserve the same type of node attributes or relationships, which cannot effectively work on heterogeneous graphs due to the complexity. To address this issue, we propose a novel heterogeneous graph neural network privacy-preserving method based on a differential privacy mechanism named HeteDP, which provides a double guarantee on graph features and topology. In particular, we first define a new attack scheme to reveal privacy leakage in the heterogeneous graphs. Specifically, we design a two-stage pipeline framework, which includes the privacy-preserving feature encoder and the heterogeneous link reconstructor with gradients perturbation based on differential privacy to tolerate data diversity and against the attack. To better control the noise and promote model performance, we utilize a bi-level optimization pattern to allocate a suitable privacy budget for the above two modules. Our experiments on four public benchmarks show that the HeteDP method is equipped to resist heterogeneous graph privacy leakage with admirable model generalization.

关键词： Training Privacy Differential privacy Social networking (online) Graph neural networks Topology Resource management

来源：评论

学校读者我要写书评

暂无评论

Automated Classification of Attacker Privileges Based on Deep Neural Network 1

引用

4th International Conference on Smart computing and Communications, SmartCom 2019

作者： Liu, Hailong Li, Bo Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China

ISBN: (数字)9783030341398

ISBN: (纸本)9783030341381

Attack graphs generated from the detected vulnerabilities in a network depict all possible attack paths that an intruder can take. Conventional approaches to generating attack graphs require well-categorized data of prerequisites and postconditions for the identified vulnerabilities. However, generating them in an automated way is an open issue. Hence automatic classification methods are desirable to effectively generate attacker privilege fields as prerequisites and postconditions, improve the generation of the attack graph, and reduce the security risks of the system. In this paper, we propose a new automatic attacker privilege model (IG-DNN). The information gain (IG) is used for obtaining an optimal set of feature words from vulnerability description, and the deep neural network model is served as an automatic attacker privilege classifier. We use the National Vulnerability database (NVD) to validate the effectiveness of the IG-DNN model. We observe that prerequisite and postcondition privileges can be generated with overall average F-measure of 99.53% and 98.90% with the IG-DNN models, respectively. Moreover, compared with Naïve Bayes, KNN, and SVM, the IG-DNN model has achieved the best performance in precision, recall, and F-measure. © 2019, Springer Nature Switzerland AG.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-Aware Relational Graph Neural Network for Few-Shot Knowledge Graph Completion

arXiv

引用

arXiv 2024年

作者： Li, Qian Guo, Shu Chen, Yingjia Ji, Cheng Sheng, Jiawei Li, Jianxin Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100083 China The State Key Laboratory of Software Development Environment Beihang University Beijing100083 China National Computer Network Emergency Response Technical Team Coordination Center of China Beijing100083 China School of Mathematics Edinburgh University Edinburgh United Kingdom Institute of Information Engineering Chinese Academy of Sciences Beijing100083 China School of Cyber Security University of Chinese Academy of Sciences Beijing100083 China

Few-shot knowledge graph completion (FKGC) aims to query the unseen facts of a relation given its few-shot reference entity pairs. The side effect of noises due to the uncertainty of entities and triples may limit the few-shot learning, but existing FKGC works neglect such uncertainty, which leads them more susceptible to limited reference samples with noises. In this paper, we propose a novel uncertainty-aware few-shot KG completion framework (UFKGC) to model uncertainty for a better understanding of the limited data by learning representations under Gaussian distribution. Uncertainty representation is first designed for estimating the uncertainty scope of the entity pairs after transferring feature representations into a Gaussian distribution. Further, to better integrate the neighbors with uncertainty characteristics for entity features, we design an uncertainty-aware relational graph neural network (UR-GNN) to conduct convolution operations between the Gaussian distributions. Then, multiple random samplings are conducted for reference triples within the Gaussian distribution to generate smooth reference representations during the optimization. The final completion score for each query instance is measured by the designed uncertainty optimization to make our approach more robust to the noises in few-shot scenarios. Experimental results show that our approach achieves excellent performance on two benchmark datasets compared to its competitors. Copyright © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Neuromodulated Meta-Learning

arXiv

引用

arXiv 2024年

作者： Wang, Jingyao Guo, Huijie Qiang, Wenwen Li, Jiangmeng Zheng, Changwen Xiong, Hui Hua, Gang University of Chinese Academy of Sciences Beijing China National Key Laboratory of Space Integrated Information System Institute of Software Chinese Academy of Sciences Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China Thrust of Artificial Intelligence Hong Kong University of Science and Technology Guangzhou China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Wormpex AI Research LLC BellevueWA98004 United States

Humans excel at adapting perceptions and actions to diverse environments, enabling efficient interaction with the external world. This adaptive capability relies on the biological nervous system (BNS), which activates different brain regions for distinct tasks. Meta-learning similarly trains machines to handle multiple tasks but relies on a fixed network structure, not as flexible as BNS. To investigate the role of flexible network structure (FNS) in meta-learning, we conduct extensive empirical and theoretical analyses, finding that model performance is tied to structure, with no universally optimal pattern across tasks. This reveals the crucial role of FNS in meta-learning, ensuring meta-learning to generate the optimal structure for each task, thereby maximizing the performance and learning efficiency of meta-learning. Motivated by this insight, we propose to define, measure, and model FNS in meta-learning. First, we define that an effective FNS should possess frugality, plasticity, and sensitivity. Then, to quantify FNS in practice, we present three measurements for these properties, collectively forming the structure constraint with theoretical supports. Building on this, we finally propose Neuromodulated Meta-Learning (NeuronML) to model FNS in meta-learning. It utilizes bi-level optimization to update both weights and structure with the structure constraint. Extensive theoretical and empirical evaluations demonstrate the effectiveness of NeuronML on various tasks. Code is publicly available at https://***/WangJingyao07/NeuronML. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Optimal Location for Electric Vehicles Charging Stations Based on P-Median Model 6th

Optimal Location for Electric Vehicles Charging Stations Bas...

引用

6th International Conference on Artificial Intelligence and Security,ICAIS 2020

作者： Tian, Daxin Yan, Huiwen Duan, Xuting Cao, Yue Zhou, Jianshan Hao, Wei Long, Kejun Gu, Jian Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing China School of Transportation Science and Engineering Beihang University Beijing100191 China School of Traffic and Transportation Engineering Changsha University of Science and Technology Changsha410114 China

ISBN: (纸本)9789811580857

To some certain extent, the development of electric vehicles relies on the availability of infrastructure, especially charging facility. There have been a large amount of studies on the location of electric vehicle charging stations before. In this paper, we establish an improved p-median model that aims to minimize the time costs. This model has some constraints such as the capacity of charging stations and the demand of customers, etc. All of these constraints should be satisfied at the same time. In order to solve this problem, a greedy heuristic algorithm is proposed. Then, we use MATLAB to simulate the case of a real-city charging station layout, and the result indicates that our method is effective and reasonable. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Multi-aspect temporal network embedding: A mixture of Hawkes process view

arXiv

引用

arXiv 2021年

作者： Chang, Yutian Liu, Guannan Zuo, Yuan Wu, Junjie School of Economics and Management Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China Beijing Key Laboratory of Emergency Support Simulation Technologies for City Operations Beihang University

Recent years have witnessed the tremendous research interests in network embedding. Extant works have taken the neighborhood formation as the critical information to reveal the inherent dynamics of network structures, and suggested encoding temporal edge formation sequences to capture the historical influences of neighbors. In this paper, however, we argue that the edge formation can be attributed to a variety of driving factors including the temporal influence, which is better referred to as multiple aspects. As a matter of fact, different node aspects can drive the formation of distinctive neighbors, giving birth to the multi-aspect embedding that relates to but goes beyond a temporal scope. Along this vein, we propose a Mixture of Hawkes-based Temporal Network Embeddings (MHNE) model to capture the aspect-driven neighborhood formation of networks. In MHNE, we encode the multi-aspect embeddings into the mixture of Hawkes processes to gain the advantages in modeling the excitation effects and the latent aspects. Specifically, a graph attention mechanism is used to assign different weights to account for the excitation effects of history events, while a Gumbel-Softmax is plugged in to derive the distribution over the aspects. Extensive experiments on 8 different temporal networks have demonstrated the great performance of the multi-aspect embeddings obtained by MHNE in comparison with the state-of-the-art methods. Copyright © 2021, The Authors. All rights reserved.

关键词： Network embeddings

来源：评论

学校读者我要写书评

暂无评论

Stabilization of continuous-time Markov/semi-Markov jump linear systems via finite data-rate feedback

arXiv

引用

arXiv 2021年

作者： Wang, Jingyi Feng, Jianwen Xu, Chen Wu, Xiaoqun Lü, Jinhu College of Mathematics and Statistics Shenzhen University Shenzhen518060 China School of Mathematics and Statistics Hubei Key Laboratory of Computational Science Wuhan University Wuhan China State Key Laboratory of Software Development Environment School of Automation Science and Electrical Engineering Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China

This paper investigates almost sure exponential stabilization of continuous-time Markov jump linear systems (MJLSs) under communication data-rate constraints by introducing sampling and quantization into the feedback control. Different from previous works, the sampling times and the jump times are independent of each other in this paper. The quantization is recursively adjusted on the sampling time, and its updating strategy does not depend on the switching in a sampling interval. In other words, the explicit value of the switching signal in a sampling interval is not necessary. The numerically testable condition is developed to ensure almost sure exponential stabilization of MJLSs under the proposed communication and control protocols. We also drop the assumption of stabilizability of all individual modes required in previous works about the switched systems. Moreover, we extend the result to the case of continuous-time semi-Markov jump linear systems (semi-MJLSs) via the semi-Markov kernel approach. Finally, some numerical examples are presented to illustrate the effectiveness on stabilization of the proposed communication and control *** Codes 93D15 © 2021, CC BY.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Grammars and a random generator for deterministic chain regular expressions 46

Grammars and a random generator for deterministic chain regu...

引用

46th International Conference on Current Trends in Theory and Practice of Computer Science Doctoral Student Research Forum, SOFSEM-SRF 2020

作者： Chu, Xinyu Lu, Ping Chen, Haiming State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China

Deterministic regular expressions (DREs) are a core part of XML Schema and widely used in other applications. There are context-free grammars for DREs, which are not efficient for being used and also lead to the problem of being unable to generate expressions of the given length in an efficient manner. Deterministic chain regular expressions (dCHAREs) are a very practical subclass of DREs. In many practical situations, dCHAREs are more suitable than standard or deterministic regular expressions. But dCHAREs do not have a simple syntax, which puts a burden on the applications of these expressions. In this paper, we propose derivation rules and give regular grammars for dCHAREs which are more succinct than the grammars of DREs. Based on the grammars, we further design an algorithm to randomly generate dCHAREs of the given length, which fills the gap in the generation of DREs. Experimental results demonstrate that our generator is efficient in terms of running time and complexity. Copyright © 2020 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Pattern matching

来源：评论

学校读者我要写书评

暂无评论

Cyber threat intelligence modeling based on heterogeneous graph convolutional network 23

Cyber threat intelligence modeling based on heterogeneous gr...

引用

23rd International Symposium on Research in Attacks, Intrusions and Defenses, RAID 2020

作者： Zhao, Jun Yan, Qiben Liu, Xudong Li, Bo Zuo, Guangsheng School of Computer Science and Engineering Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China Computer Science and Engineering Michigan State University East LansingMI United States

ISBN: (纸本)9781939133182

Cyber Threat Intelligence (CTI), as a collection of threat information, has been widely used in industry to defend against prevalent cyber attacks. CTI is commonly represented as Indicator of Compromise (IOC) for formalizing threat actors. However, current CTI studies pose three major limitations: first, the accuracy of IOC extraction is low;second, isolated IOC hardly depicts the comprehensive landscape of threat events;third, the interdependent relationships among heterogeneous IOCs, which can be leveraged to mine deep security insights, are unexplored. In this paper, we propose a novel CTI framework, HINTI, to model the interdependent relationships among heterogeneous IOCs to quantify their relevance. Specifically, we first propose multi-granular attention based IOC recognition method to boost the accuracy of IOC extraction. We then model the interdependent relationships among IOCs using a newly constructed heterogeneous information network (HIN). To explore intricate security knowledge, we propose a threat intelligence computing framework based on graph convolutional networks for effective knowledge discovery. Experimental results demonstrate that our proposed IOC extraction approach outperforms existing state-of-the-art methods, and HINTI can model and quantify the underlying relationships among heterogeneous IOCs, shedding new light on the evolving threat landscape. © 2020 by The USENIX Association. All Rights Reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Adaptive Surrogate Model for Failure Probability Estimation 21

Adaptive Surrogate Model for Failure Probability Estimation

引用

5th International Conference on Computer Science and Application Engineering, CSAE 2021

作者： Qin, Yi Zhang, Yue Liu, Zexin Zhu, Xueyu Wang, Peng School of Mathematical Sciences Beihang University Haidian District Beijing China School of Integrated Circuit Science and Engineering Beihang University Haidian District Beijing China Department of Mathematics University of Utah Salt Lake CityUtah United States Scientific Computing and Imaging Institute University of Utah Salt Lake CityUtah United States Department of Mathematics University of Iowa Iowa City United States Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Haidian District Beijing China

ISBN: (纸本)9781450389853

Estimating failure probability becomes a fundamental task in many complex engineering designs and optimizations. Yet, evaluation of failure probability via direct sampling from a given system can be computationally expensive and sometimes impossible. Although the construction of a response surface/surrogate could reduce such computational cost, reliance on its sampling alone may still yield an erroneous estimate of the failure probability. In this paper, we employ generalized polynomial chaos and develop an adaptive method whose surrogate model evolves with the additional data sampled from the underlying system as the iteration proceeds. It is more flexible by not requiring an accurate surrogate model in priori. Via three distinct numerical examples and one practical problem on a spintronic device, we demonstrate that our novel scheme provides an efficient tool to estimate system failure probability.. © 2021 Association for computing Machinery. All rights reserved.

关键词： Iterative methods

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：