2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC)最新文献_第2页

Two-stage encoding Extractive Summarization 两阶段编码提取摘要

2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC) Pub Date : 2020-07-01 DOI: 10.1109/DSC50466.2020.00060

Wenying Guo, Bin Wu, Bai Wang, Yuanyu Yang

{"title":"Two-stage encoding Extractive Summarization","authors":"Wenying Guo, Bin Wu, Bai Wang, Yuanyu Yang","doi":"10.1109/DSC50466.2020.00060","DOIUrl":"https://doi.org/10.1109/DSC50466.2020.00060","url":null,"abstract":"Pre-trained language model can express the semantics of word or text span, is widely applied in many NLP tasks, and text summarization is no exception. It is created using fine-tuning or feature-based method on pre-training model. Since Bidirectional Encoder Representations from Transformers (BERT; Devlin et al. 2019), many works model text summarization based on BERT, and fine tune all the parameters end-to-end. Notably, multiple research proposed different strategies to create enhanced versions of BERT further, which achieve the state-of-the-art performance in many NLP tasks. In this paper, we explore the potential of multiple versions of BERT to handle text summarization. We present a two-stage encoder model (TSEM) for extractive summarization. The first stage applies A Lite BERT (ALBERT; Lan et al. 2019) to secure sentence-level embedding, identify valuable content based on A Lite BERT (ALBERT; Lan et al. 2019). The second stage proposes a new strategy to fine-tune BERT deriving meaningful document embedding, then select the best-matched combination of important sentences with source document to compose summarization. Experimental result on the CNN/Daily Mail dataset demonstrates that our model is competitive with the state-of-the-art result.","PeriodicalId":423182,"journal":{"name":"2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123845650","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

A Safety-Enhanced Dijkstra Routing Algorithm via SDN Framework 基于SDN框架的安全增强Dijkstra路由算法

2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC) Pub Date : 2020-07-01 DOI: 10.1109/DSC50466.2020.00067

Jinjing Zhao, Ling Pang, Hong-jie Li, Zibin Wang

引用次数: 5

Longitudinal Analysis of Cyber-Related Articles 网络相关文章的纵向分析

2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC) Pub Date : 2020-07-01 DOI: 10.1109/DSC50466.2020.00038

Mohammad Al Boni, Trishala Neeraj

引用次数: 0

Join-based Social Ridesharing 基于加入的社交拼车

2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC) Pub Date : 2020-07-01 DOI: 10.1109/DSC50466.2020.00050

Yu Han, Yifei Li, Qingshun Wu, Ji Wan, Yafei Li

{"title":"Join-based Social Ridesharing","authors":"Yu Han, Yifei Li, Qingshun Wu, Ji Wan, Yafei Li","doi":"10.1109/DSC50466.2020.00050","DOIUrl":"https://doi.org/10.1109/DSC50466.2020.00050","url":null,"abstract":"Social ridesharing becomes a promising and attractive solution to settle the trust and safety problems for current ridesharing service. In a typical social ridesharing, drivers and riders submit ride requests and ride offers to the service platform via their smart phones, respectively. Specifically, for each driver, the service platform provides a set of matching riders by taking into account trip similarities and social connections. A limitation of this approach is that they assume drivers arrive in the service platform in a stream fashion and the matching of driver and rider is processed in a snapshot model. To some extent, however, this approach may reduce the success rate of matching over the whole drivers and riders. In addressing this weakness, in this paper we propose a novel Join-based Ride Matching (JbRM) model where drivers’ ride offers and riders’ ride requests are processed in a join-based approach to achieve best utility over a time window. JbRM problem is indeed of practical usefulness, we design several efficient algorithms with a set of powerful pruning techniques to tackle this problem. Extensive experiments conducted on real-life datasets show that our proposed algorithms achieve desirable performance.","PeriodicalId":423182,"journal":{"name":"2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC)","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133889222","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Deep Learning for Social Network Information Cascade Analysis: a survey 深度学习在社交网络信息级联分析中的应用

2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC) Pub Date : 2020-07-01 DOI: 10.1109/DSC50466.2020.00022

Liqun Gao, Bin Zhou, Yan Jia, Hongkui Tu, Ye Wang, Chenguang Chen, Haiyang Wang, Hongwu Zhuang

{"title":"Deep Learning for Social Network Information Cascade Analysis: a survey","authors":"Liqun Gao, Bin Zhou, Yan Jia, Hongkui Tu, Ye Wang, Chenguang Chen, Haiyang Wang, Hongwu Zhuang","doi":"10.1109/DSC50466.2020.00022","DOIUrl":"https://doi.org/10.1109/DSC50466.2020.00022","url":null,"abstract":"The phenomenon of information dissemination in social networks is widespread, and Social Network Information Cascade Analysis (SNICA) aims to acquire valuable knowledge in the process of information dissemination in social networks. As the number, volume, and resolution of social network data increase rapidly, traditional social network data analysis methods, especially the analysis method of social network graph (SNG) data becoming overwhelmed in SNICA. Recently, deep learning models have changed this situation, and it has achieved success in SNICA with its powerful implicit feature extraction capabilities. In this paper, we provide a comprehensive survey of recent progress in applying deep learning techniques for SNICA. We first introduce related concepts and summarize the advantages of deep learning technology in SNICA. Then, we propose a general framework for deep learning technology, which applies to SNICA. Then, different SNICA application scenarios in the framework are classified and discussed according to user behavior analysis, information cascade analysis, rumor detection, and social network event analysis. Finally, we discuss the limitations of current work and suggest future directions.","PeriodicalId":423182,"journal":{"name":"2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128636840","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

Malicious Code Detection Technology Based on Metadata Machine Learning 基于元数据机器学习的恶意代码检测技术

2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC) Pub Date : 2020-07-01 DOI: 10.1109/DSC50466.2020.00068

Zhongru Wang, P. Cong, Weiqiang Yu

引用次数: 1

Seeds Optimization for Entity Alignment in Knowledge Graph Embedding 知识图嵌入中实体对齐的种子优化

2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC) Pub Date : 2020-07-01 DOI: 10.1109/DSC50466.2020.00058

Xiaolong Chen, Le Wang, Yunyi Tang, Weihong Han, Zhaoquan Gu

引用次数: 2

DSC 2020 TOC

2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC) Pub Date : 2020-07-01 DOI: 10.1109/dsc50466.2020.00004

引用次数: 0

StateConsisIV: A Privacy-preserving Integrity Verification Method for Cloud Components Based on a Novel State Consistency Feature StateConsisIV:一种基于状态一致性特征的云组件完整性保护方法

2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC) Pub Date : 2020-07-01 DOI: 10.1109/DSC50466.2020.00026

Peiru Fan, Chonghua Wang, Jun Li, B. Zhao, Zhaoxu Ji

{"title":"StateConsisIV: A Privacy-preserving Integrity Verification Method for Cloud Components Based on a Novel State Consistency Feature","authors":"Peiru Fan, Chonghua Wang, Jun Li, B. Zhao, Zhaoxu Ji","doi":"10.1109/DSC50466.2020.00026","DOIUrl":"https://doi.org/10.1109/DSC50466.2020.00026","url":null,"abstract":"Plain proofs (e.g., raw logs, report, etc.) are significant and effective for integrity verification. In our analysis and comparison of existing work, we found most of them did not employ any protection mechanisms on the proofs. However, these proofs contain sensitive information, which may cause privacy leakage risks when the third party verifier (TPV) is compromised. The situation is even worse when the verification objects are cloud components. Motivated by this, we present StateConsisIV, a privacy-preserving integrity verification method based on a novel state consistency feature to address the privacy leakage problem. The core idea of our work is to enable the integrity judgment through encrypted proofs, withholding plain proofs inside the cloud only to reduce attack surface and enhance privacy. In specific, we employ random transformation algorithm on cloud nodes to encrypt proofs on their birth places. Besides, we design a novel state consistency feature based on the deployment and operation pattern of structural cloud components and perform feature analysis on TPV to guarantee an accurate integrity judgment result. We evaluate our approach on one typical dataset. The experimental results show that our method is considered more worthy with a little bit of extra computation overhead.","PeriodicalId":423182,"journal":{"name":"2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116571471","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

DSC 2020 Breaker Page DSC 2020断路器页面

2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC) Pub Date : 2020-07-01 DOI: 10.1109/dsc50466.2020.00003

引用次数: 0