Lap Q. Trieu, Trung-Nguyen Tran, Mai-Khiem Tran, Minh-Triet Tran
{"title":"Document Sensitivity Classification for Data Leakage Prevention with Twitter-Based Document Embedding and Query Expansion","authors":"Lap Q. Trieu, Trung-Nguyen Tran, Mai-Khiem Tran, Minh-Triet Tran","doi":"10.1109/CIS.2017.00125","DOIUrl":"https://doi.org/10.1109/CIS.2017.00125","url":null,"abstract":"Document sensitivity classification is essential to prevent potential sensitive data leakage for individuals and organizations. As most of existing methods use regular expressions or data fingerprinting to classify sensitive documents, they may not fully exploit the semantic and content of a document, especially with informal messages and files. This motivates the authors to propose a novel method to classify document sensitivity in realtime with better semantic and content analysis. Taking advantages of deep learning in natural language processing, we use our pre-trained Twitter-based document embedding TD2V to encode a document or a text fragment into a fixed length vector of 300 dimensions. Then we use retrieval and automatic query expansion to retrieve a re-ranked list of semantically similar known documents, and determine the sensitivity score for a new document from those of the retrieved documents in this list. Experimental results show that our method can achieve classification accuracy of more than 99.9% for 4 datasets (snowden, Mormon, Dyncorp, TM) and 98.34% for Enron dataset. Furthermore, our method can early predict a sensitive document from a short text fragment with the accuracy higher than 98.84%.","PeriodicalId":304958,"journal":{"name":"2017 13th International Conference on Computational Intelligence and Security (CIS)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114466684","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}
{"title":"Unsupervised Off-Topic Essay Detection Based on Target and Reference Prompts","authors":"xia li, Qifan Wen, Kongxin Pan","doi":"10.1109/CIS.2017.00108","DOIUrl":"https://doi.org/10.1109/CIS.2017.00108","url":null,"abstract":"Off-topic essay detection is an important part of the automatic essay scoring systems. Prior works mainly focused on the semantic similarity between the essay and the target prompt without considering the similarities between the essay and the reference prompts, while the latter can provide more semantic information on detecting off-topic essays. In this paper, an improved on-topic scores calculation method is proposed to improve the accuracy of off-topic essay detection. In our approach, we use the semantic difference between the similarities of the essay with the target prompt and that of with the reference prompts to on-topic score calculation, which is used to better distinguish the on-topic essays and the off-topic essays. Based on our new on-topic score method, we realize an unsupervised off-topic essay detection system without large scale of training data. Several experiments on six datasets of Kaggle competition show that our method can effectively detect off-topic essay.","PeriodicalId":304958,"journal":{"name":"2017 13th International Conference on Computational Intelligence and Security (CIS)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123892444","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}
{"title":"Binary Histogram of Oriented Gradients Based Dynamometer Card Recognition","authors":"Xiaoma Xu, Renbin Gong, Yinghao Li, Jinnuo Li, Qun Li, Zhenzhen Xu","doi":"10.1109/CIS.2017.00032","DOIUrl":"https://doi.org/10.1109/CIS.2017.00032","url":null,"abstract":"Surface dynamometer card of pumping unit is a closed curve of load and displacement values in a pumping cycle, which reflects the operating condition of the sucker-rod pumping unit. Automatic analyzing and diagnosing the dynamometer card plays an important role in the process of oil and gas production. This paper proposes a robust Binary Histogram of Oriented Gradients (BHOG) feature for dynamometer card recognition. It is much simpler and more effective than the general HOG feature and has great performance. BHOG feature represents the binary image by 4 kinds of texture (corresponding to 4 bins of histogram in HOG), could highly reduce the feature size. Besides, the process of feature extraction has also been simplified. Experiment shows that the proposed BHOG feature is 5.32 times faster than the general HOG feature, and achieves 98.19% accuracy in the dynamometer card dataset.","PeriodicalId":304958,"journal":{"name":"2017 13th International Conference on Computational Intelligence and Security (CIS)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124296552","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}
{"title":"Research on Video Server Placement and Flux Plan Based on GA","authors":"Long Zhao, Jingxuan Wei, Minghan Li","doi":"10.1109/CIS.2017.00016","DOIUrl":"https://doi.org/10.1109/CIS.2017.00016","url":null,"abstract":"The paper is about a research on a problem of placing video servers and planning fluxes in an existing network topology, which must meet both the broadband limits and user's needs. For this problem, we build a bilevel mode and design two algorithms, in which the genetic algorithm is used to optimize the upper target and the SPFA minimum cost flow algorithm is used for lower target. Experimental results show that, in a complex network with large nodes and dense links, the proposed algorithm can gain a better server deployment solution in a relatively short period of time.","PeriodicalId":304958,"journal":{"name":"2017 13th International Conference on Computational Intelligence and Security (CIS)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123239180","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}
Imen Khabou, M. Rouached, Alexandre Viejo, David Sánchez
{"title":"Using Searchable Encryption for Privacy-Aware Orchestrated Web Service Composition","authors":"Imen Khabou, M. Rouached, Alexandre Viejo, David Sánchez","doi":"10.1109/CIS.2017.00073","DOIUrl":"https://doi.org/10.1109/CIS.2017.00073","url":null,"abstract":"Among all the applications in which Web service composition may be applied, this paper focuses on a cloud-based scenario in which a business targets to outsource the execution of a certain complex service in exchange for some economical compensation. It propose a privacy-preserving orchestrated Web service compositions system using a symmetric searchable encryption primitive. The new proposal ensures that the composer is not able to access the data of the users as well as any information on invoked activities, whereas service providers are able to access only the portions of user preferences and service parameters needed for the correct execution of the specific and atomic assigned activities.","PeriodicalId":304958,"journal":{"name":"2017 13th International Conference on Computational Intelligence and Security (CIS)","volume":"216 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121295739","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}
{"title":"Student Behavior Clustering Method Based on Campus Big Data","authors":"Dong Ding, Junhuai Li, Huaijun Wang, Zhu Liang","doi":"10.1109/CIS.2017.00116","DOIUrl":"https://doi.org/10.1109/CIS.2017.00116","url":null,"abstract":"Nowadays, a large amount of valuable data have been accumulated. According to the big data from the management system of university, we attempt to subdivide students' behavior into different groups from various aspects, so as to identifying the different groups of students. Given this, this paper can get the characteristics of students from different groups. In this way, universities can know students well and manage them reasonably. First, in order to solve the segmentation of student behavior, this paper presents a set of description index system of student behavior and the segmentation model of student behavior based on clustering analysis. Meanwhile, in order to obtain more accurate clustering results, the traditional K-Means clustering algorithm is improved from the selection of the initial clustering center and the number of clusters. In addition, the improved method is parallelized on the Spark platform and applied to subdivide student behavior into different groups. Finally, experiments are conducted to verify the reliability of the results.","PeriodicalId":304958,"journal":{"name":"2017 13th International Conference on Computational Intelligence and Security (CIS)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126255579","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}
{"title":"A Review of Sentiment Semantic Analysis Technology and Progress","authors":"Yimin Wang, Y. Rao, Lianwei Wu","doi":"10.1109/CIS.2017.00105","DOIUrl":"https://doi.org/10.1109/CIS.2017.00105","url":null,"abstract":"Sentiment computing brings some new application opportunities and technique challenges in artificial intelligence of the next generation, and it has become a fascinating research field. In this paper, the conception of sentiment computing with some core elements and feature vectors is defined, and some vital issues are proposed. Based on the theories mentioned above, the subjective content or objective content is classified by some special algorithms in the scenarios of single modal, such as text, image, audio and video data. Furthermore, how to merge these different kinds of data and to form the multimodal analysis methods for emotion detection is an important problem, and the fusion strategy is summarized in the paper. Finally, some trends about the sentiment cognition and sentiment generation are analyzed, which provides new ways for further research work.","PeriodicalId":304958,"journal":{"name":"2017 13th International Conference on Computational Intelligence and Security (CIS)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126664747","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}
{"title":"Kernelised Rényi Distance for Localization and Mapping of Autonomous Vehicle","authors":"Guangjing Li, H. Bao, Bo Wang, Tao Wu","doi":"10.1109/CIS.2017.00023","DOIUrl":"https://doi.org/10.1109/CIS.2017.00023","url":null,"abstract":"Accurate locating is an important task for autonomous vehicles' safely driving. In order to realize the precise locating autonomous vehicles without Global Positioning System(GPS) signal, a Kernelized Rényi Distance(KRD) based simultaneous localization and mapping(SLAM) algorithm is proposed in this paper. In our Algorithm, pose estimation are computed by optimizing KRD between two groups of laser point(in odometry process) or between laser points and the local map(in mapping process). The experimental results indicate that the proposed algorithm can accurately locate autonomous vehicle and build the traveled environment map.","PeriodicalId":304958,"journal":{"name":"2017 13th International Conference on Computational Intelligence and Security (CIS)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122372304","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}
{"title":"New Protocols on Group Consensus of Continuous-Time Multi-agent Systems","authors":"Xinlei Feng, Xiaoli Yang","doi":"10.1109/CIS.2017.00025","DOIUrl":"https://doi.org/10.1109/CIS.2017.00025","url":null,"abstract":"In this paper, we consider a kind of new protocols on group consensus in which communication weights of topology graph are all non-negative. This is also different with general group consensus protocols. Necessary and sufficient conditions which group consensus under these protocols can reach are obtained for the first, second and high order continuous-time multi-agent system. Finally, numerical examples are used to illustrate our theoretical results.","PeriodicalId":304958,"journal":{"name":"2017 13th International Conference on Computational Intelligence and Security (CIS)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133609702","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}
{"title":"A New Optimization Model and Algorithm for a Network Scheduling Problem in Inter-Datacenters Elastic Optical Networks","authors":"Hejun Xuan, Yuping Wang, Shiwei Guan, Zhanqi Xu","doi":"10.1109/CIS.2017.00015","DOIUrl":"https://doi.org/10.1109/CIS.2017.00015","url":null,"abstract":"The routing and virtual network function (VNF) deployment for VNF service chaining in inter-datacenters elastic optical networks (inter-DC EONs) is an important network scheduling problem. In this paper, the problem tackled is more complex and practical than those tackled in the existing works in the following three aspects: 1) each datacenter can only provide some specific (not all) VNFs; 2) the resource of both bandwidth and datacenters system (not the resource of bandwidth only) is considered; 3) a part of VNFs are dependent (not assuming all VNFs are independent). To solve this challenging problem, we first establish a global optimization model for this problem. Then, an efficient genetic algorithm with tailor-made encoding scheme is proposed to solve the model. Finally, the simulation experiments are conducted on several situations, and the results indicate that the proposed model is reasonable and the proposed algorithm is efficient.","PeriodicalId":304958,"journal":{"name":"2017 13th International Conference on Computational Intelligence and Security (CIS)","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134540454","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}