Filters








2,998 Hits in 8.6 sec

Cash-Out User Detection Based on Attributed Heterogeneous Information Network with a Hierarchical Attention Mechanism

Binbin Hu, Zhiqiang Zhang, Chuan Shi, Jun Zhou, Xiaolong Li, Yuan Qi
2019 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
In this paper, with the real datasets in Ant Credit Pay of Ant Financial Services Group, we first study the cashout user detection problem and propose a novel hierarchical attention mechanism based cash-out  ...  As one of the major frauds in financial services, cash-out fraud is that users pursue cash gains with illegal or insincere means.  ...  In this paper, we first study the cash-out detection problem under the AHIN framework, and propose a novel Hierarchical Attention mechanism based Cash-out User Detection model, called HACUD.  ... 
doi:10.1609/aaai.v33i01.3301946 fatcat:4k22nudqhzbzhakfr2fbonfsni

Heterogeneous Information Network based Default Analysis on Banking Micro and Small Enterprise Users [article]

Zheng Zhang, Yingsheng Ji, Jiachen Shen, Xi Zhang, Guangwen Yang
2022 arXiv   pre-print
Specifically, we attempt to incorporate heterogeneous information network with rich attributes on multi-typed nodes and links for modeling the scenario of business banking service.  ...  Furthermore, we devise a hierarchical attention mechanism respectively to learn the importance of contents inside each meta-path and the importance of different metapahs.  ...  [12] considered node information and proposed an attributed heterogeneous information network (AHIN) for cash-out fraud detection. Hu et al.  ... 
arXiv:2204.11849v2 fatcat:jljivqnsrvdczi26valy5o6luy

A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources [article]

Xiao Wang and Deyu Bo and Chuan Shi and Shaohua Fan and Yanfang Ye and Philip S. Yu
2020 arXiv   pre-print
Heterogeneous graphs (HGs) also known as heterogeneous information networks have become ubiquitous in real-world scenarios; therefore, HG embedding, which aims to learn representations in a lower-dimension  ...  survey and categorize the state-of-the-art HG embedding methods based on the information they used in the learning process to address the challenges posed by the HG heterogeneity.  ...  , called HACUD, to classify the cash-out user.  ... 
arXiv:2011.14867v1 fatcat:phfoxj7qsrfshfednomeok7pau

A Semi-Supervised Graph Attentive Network for Financial Fraud Detection

Daixin Wang, Yuan Qi, Jianbin Lin, Peng Cui, Quanhui Jia, Zhen Wang, Yanming Fang, Quan Yu, Jun Zhou, Shuang Yang
2019 2019 IEEE International Conference on Data Mining (ICDM)  
Moreover, we propose a hierarchical attention mechanism to better correlate different neighbors and different views.  ...  By utilizing the social relations and the user attributes, our method can achieve a better accuracy compared with the state-of-the-art methods on two tasks.  ...  [5] proposes a graph neural network for malicious account detection. Hu et al. [6] proposes a meta-path based graph embedding method for user cash-out prediction.  ... 
doi:10.1109/icdm.2019.00070 dblp:conf/icdm/WangQL0JWFYZY19 fatcat:6nmk42i4rrbcljhw66vggr47qq

Detecting Senior Executives' Personalities for Predicting Corporate Behaviors: An Attention-based Deep Learning Approach

Kai Yang, Raymond Y. K. Lau
2019 International Conference on Information Systems  
First, we design a novel deep learning-based artifact, namely pAttCLSTM which analyzes the senior executives' personalities on a large scale through social media data.  ...  Second, empowered by pAttCLSTM, we empirically verify the predictive power of executives' personalities on firms' policy variables by using a dataset including Tweets of 507 executives worked in S&P 1500  ...  Acknowledgement This study was partially supported by a grant from the RGC Hong Kong (Project: CityU 11502115), and the NSFC Basic Research Program (Project: 71671155), and the City University of Hong  ... 
dblp:conf/icis/YangL19 fatcat:hmbzvatw25c2debalicx6frfya

Use of Ontologies for Metadata Records Analysis in Big Data

Julia V. Rogushina, Anatoly Jasonovich Gladun, Serhii M. Pryima
2018 International Scientific and Practical Conference "Information Technologies and Security"  
Big Data deals with the sets of information (structured, unstructured, or semi structured) so large that traditional ways and approaches (based on business intelligence decisions and database management  ...  In the paper, the authors present a method for analyzing the Big Data metadata which allows selecting those blocks of information among the heterogeneous sources and data repositories that are pertinent  ...  Such a mechanism can be based the task thesaurus which represents the user needs of base of the domain ontology.  ... 
dblp:conf/its2/RogushinaGP18 fatcat:fof3wy6tafg5nljysixd57mzeu

Agent-based host enumeration and vulnerability scanning using dynamic topology information

Ziyad S. Al-Salloum, Stephen D. Wolthusen
2010 2010 Information Security for South Africa  
In this paper we therefore propose an agent-based semiautonomous scanning mechanism which utilizes topology information to traverse networks with minimum bandwidth usage and maximum network coverage, and  ...  Topology information is also used to constrain propagation to a well defined network, while intermittently active hosts and topology changes are detected by using resident reactive agents plotted throughout  ...  Our mechanism, however, avoid scanning non-existent IP addresses since it detect targets based on CAM information. XIII.  ... 
doi:10.1109/issa.2010.5588317 fatcat:4tktlam3x5hrjkczntpzic6dmm

A SURVEY ON NEW APPROACHES OF INTERNET OF THINGS DATA MINING

Sallauddin Mohmmad
2017 International Journal of Advanced Research in Computer Science  
Configuring an IoT middleware layer and retrieving data is a big challenge for data consumers .In this paper, we survey on how IoT data can be produce and in such away automated knowledge discovery from  ...  Many number of devices are associated with IoT, massive amount of volume data producing every day.Data Mining is a process of mining required data from databases in efficient way and obtaining optimized  ...  applications need to be configured depends on the context of sensor information and user requirements.  ... 
doi:10.26483/ijarcs.v8i8.4849 fatcat:ojpxgnxrtjbzlhnqkzmlvlwu6y

A Survey on Metaverse: Fundamentals, Security, and Privacy [article]

Yuntao Wang, Zhou Su, Ning Zhang, Dongxiao Liu, Rui Xing, Tom H. Luan, Xuemin Shen
2022 arXiv   pre-print
Specifically, we first investigate a novel distributed metaverse architecture and its key characteristics with ternary-world interactions.  ...  realism, hyper spatiotemporality, sustainability, and heterogeneity.  ...  [129] propose a time-domain attribute-based access control mechanism with provable security for sharing user-generated video contents (UGVCs) in the cloud.  ... 
arXiv:2203.02662v2 fatcat:k5ba4o3lbbarljwgrrqftamlue

A Survey of Security Architectures for Edge Computing-Based IoT

Elahe Fazeldehkordi, Tor-Morten Grønli
2022 IoT  
Next, we propose a secure EC-based architecture for IoT applications.  ...  Edge computing (EC) is a promising strategy to overcome these challenges by bringing data processing and storage close to end users and IoT devices.  ...  Informed Consent Statement: Not applicable. Data Availability Statement: It has been a project together with Fluxloop company. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/iot3030019 fatcat:vxwo2kklxrcb7a4vqzncpx5qwy

Suicidal Ideation Detection: A Review of Machine Learning Methods and Applications [article]

Shaoxiong Ji and Shirui Pan and Xue Li and Erik Cambria and Guodong Long and Zi Huang
2020 arXiv   pre-print
engineering or deep learning for automatic detection based on online social contents.  ...  Current suicidal ideation detection methods include clinical methods based on the interaction between social workers or experts and the targeted individuals and machine learning techniques with feature  ...  For example, Cash et al. [93] conducted a study on adolescents' comments and content analysis on MySpace. Steaming data provides a good source for user pattern analysis. Vioulès et al.  ... 
arXiv:1910.12611v2 fatcat:63z4uvh5zrgyzb2bawtlbuo34m

Bridging Socially Enhanced Virtual Communities

Venugopal Rao
2013 IOSR Journal of Computer Engineering  
The empirical results revealed that the proposed system is effective when tested with test bed which is based on distributed technology such as web services.  ...  As technologies required for collaborative computing grow, there are business collaborations among companies carrying out related business.  ...  help given to us in the completion of our project titled, 'Video Watermarking scheme based on DWT and PCA for copyright protection'.  ... 
doi:10.9790/0661-0940104 fatcat:zejgpenvqzb7rkchkznv5igfwm

Combatting Insider Threats [chapter]

Peter G. Neumann
2010 Advances in Information Security  
Trustworthy system developments must consider insider misuse as merely one set of threats that must be addressed consistently together with many other threats such as penetrations, denials of service,  ...  This chapter seeks to cope with insider misuse in a broad range of application domainsfor example, critical infrastructures, privacy-preserving database systems, financial systems, and interoperable health-care  ...  • Monitoring: Data from appropriate audit trails (operating systems, DBMSs, applications) and network data (packets, network management information) needs to be hierarchically abstracted, heterogeneous  ... 
doi:10.1007/978-1-4419-7133-3_2 fatcat:nlrc6r5mibayxnsttn4rmrgvzm

Open challenges for data stream mining research

Georg Krempl, Myra Spiliopoulou, Jerzy Stefanowski, Indre Žliobaite, Dariusz Brzeziński, Eyke Hüllermeier, Mark Last, Vincent Lemaire, Tino Noack, Ammar Shaker, Sonja Sievi
2014 SIGKDD Explorations  
We study the social network structure among Tumblr users, analyze its user generated content, and describe reblogging patterns to analyze its user behavior.  ...  Existing solutions are based on "best practices", i.e., the systems' decisions are knowledge-driven and/or data-driven.  ...  Acknowledgments We would like to thank the participants of the RealStream2013 workshop at ECMLPKDD2013 in Prague, and in particular Bernhard Pfahringer and George Forman, for suggestions and discussions on  ... 
doi:10.1145/2674026.2674028 fatcat:y3bozzeohveibgxb5wmiwfcogm

Process Discovery in Business Process Management Optimization

Paweł Dymora, Maciej Koryl, Mirosław Mazurek
2019 Information  
We also compared visualizations of the outcomes of our approach with different cases and showed performance characteristics of the cash loan sales process.  ...  This paper presents a process discovery and how we can use it in a broader framework supporting self-organization in BPM. Process discovery is intrinsically associated with the process lifecycle.  ...  This mechanism is a technique for identifying information from untagged data.  ... 
doi:10.3390/info10090270 fatcat:2iji6lpxkrg4laxsdzi4j6iutu
« Previous Showing results 1 — 15 out of 2,998 results