Image Recognition Model of Fraudulent Websites Based on Image Leader Decision and Inception-V3 Transfer Learning

The fraudulent website image is a vital information carrier for telecom fraud.The efficient and precise recognition of fraudulent website images is critical to combating and dealing with fraudulent websites.Current research on image recognition of fraudulent websites is mainly carried out at the level of image feature extraction and similarity study,which have such disadvantages as difficulty in obtaining image data,insufficient image analysis,and single identification types.This study develops a model based on the entropy method for image leader decision and Inception-v3 transfer learning to address these disadvantages.The data processing part of the model uses a breadth search crawler to capture the image data.Then,the information in the images is evaluated with the entropy method,image weights are assigned,and the image leader is selected.In model training and prediction,the transfer learning of the Inception-v3 model is introduced into image recognition of fraudulent websites.Using selected image leaders to train the model,multiple types of fraudulent websites are identified with high accuracy.The experiment proves that this model has a superior accuracy in recognizing images on fraudulent websites compared to other current models.

CMAES-WFD:Adversarial Website Fingerprinting Defense Based on Covariance Matrix Adaptation Evolution Strategy

Website fingerprinting,also known asWF,is a traffic analysis attack that enables local eavesdroppers to infer a user’s browsing destination,even when using the Tor anonymity network.While advanced attacks based on deep neural network(DNN)can performfeature engineering and attain accuracy rates of over 98%,research has demonstrated thatDNNis vulnerable to adversarial samples.As a result,many researchers have explored using adversarial samples as a defense mechanism against DNN-based WF attacks and have achieved considerable success.However,these methods suffer from high bandwidth overhead or require access to the target model,which is unrealistic.This paper proposes CMAES-WFD,a black-box WF defense based on adversarial samples.The process of generating adversarial examples is transformed into a constrained optimization problem solved by utilizing the Covariance Matrix Adaptation Evolution Strategy(CMAES)optimization algorithm.Perturbations are injected into the local parts of the original traffic to control bandwidth overhead.According to the experiment results,CMAES-WFD was able to significantly decrease the accuracy of Deep Fingerprinting(DF)and VarCnn to below 8.3%and the bandwidth overhead to a maximum of only 14.6%and 20.5%,respectively.Specially,for Automated Website Fingerprinting(AWF)with simple structure,CMAES-WFD reduced the classification accuracy to only 6.7%and the bandwidth overhead to less than 7.4%.Moreover,it was demonstrated that CMAES-WFD was robust against adversarial training to a certain extent.

基于Silverlight+Websites的管理技术方案研究

Silverlight开发平台具有灵活的编程,良好的用户体验,强大的功能特点。Websites把GIS和Web有机结合,是因特网技术应用于GIS开发的产物,Web对GIS实现了扩展和完善。基于Silverlight+Websites的研究,具有良好的扩展性和交互性,应用前景广阔。本文从Silverlight开发与分析、Auto CAD和Websites的关键技术、基于Silverlight+Websites开发技术路线、管理建模四个方面进行了详细的探讨。

从The Great Websites for Kids看儿童网络资源的组织管理与评价

从机构组织、评价流程、评价标准、资源组织等方面,对美国最大的儿童网络资源导航The Great Websites for Kids(GWS)进行评述,为我国儿童网络资源的建设、管理、评价和推介提供参考。

Phishing Websites Detection by Using Optimized Stacking Ensemble Model

Phishing attacks are security attacks that do not affect only individuals’or organizations’websites but may affect Internet of Things(IoT)devices and net-works.IoT environment is an exposed environment for such attacks.Attackers may use thingbots software for the dispersal of hidden junk emails that are not noticed by users.Machine and deep learning and other methods were used to design detection methods for these attacks.However,there is still a need to enhance detection accuracy.Optimization of an ensemble classification method for phishing website(PW)detection is proposed in this study.A Genetic Algo-rithm(GA)was used for the proposed method optimization by tuning several ensemble Machine Learning(ML)methods parameters,including Random Forest(RF),AdaBoost(AB),XGBoost(XGB),Bagging(BA),GradientBoost(GB),and LightGBM(LGBM).These were accomplished by ranking the optimized classi-fiers to pick out the best classifiers as a base for the proposed method.A PW data-set that is made up of 4898 PWs and 6157 legitimate websites(LWs)was used for this study's experiments.As a result,detection accuracy was enhanced and reached 97.16 percent.

Information Network Systems and Information Sharing on Administrative Websites

In Japanese 'e-government' policy, called 'e-Japan', the 'administrative document management system' is functioning as information searching systems. On the other hand, this system has also generated the problem that it is not fully functioning as a means for the information sharing in a governmental agency. So, the purpose of this research is to find how the administrative document management system can function as information sharing in administrative organization. For this purpose, this paper considers the current status and some problems firstly. And secondary, this paper proposes the idea and constructs some information systems using administrative official Website. This is the method and approach of this research. As a conclusion, this proposal information system junctions as information sharing support systems.

Learning Association Rules and Tracking the Changing Concepts on Webpages:An Effective Pornographic Websites Filtering Approach

We applied the decision tree algorithm to learn association rules between webpage’s category(pornographic or normal) and the critical features.Based on these rules, we proposed an efficient method of filtering pornographic webpages with the following major advantages: 1) a weighted window-based technique was proposed to estimate for the condition of concept drift for the keywords found recently in pornographic webpages; 2) checking only contexts of webpages without scanning pictures; 3) an incremental learning mechanism was designed to incrementally update the pornographic keyword database.

Documental Quality of Websites Concerning Physical Activity, Lifestyle and Sedentarism Available on the Internet

Objectives: To analyze the documental quality of 389 websites in Portuguese about physical activity, healthy lifestyles and sedentary lifestyles found on the Brazilian version of the general search engine Google. Methods: The documental quality of the 389 websites was estimated based upon the following parameters: 1) a combination of quality criteria from the Health Information Locator (LIS—OPS/BIREME) and those from Chile’s Pontifical Catholic University, organized into 17 variables;2) uniformity of reference criteria (Vancouver);3) association between the presence of authorship and a higher number of the quality criteria being fulfilled. We also studied the ranking of the results presented by Google in addition to attributes connected to the websites’ target audience, the types of content, their sponsors and country of origin. Results: Of the 389 websites studied, 111 links were not active (28.53% CI 95% [24.05 - 33.02]) and none of the websites in the sample met all of the 17 quality variables. Authored websites displayed remarkable differences in quality when compared to those which did not identify their authors. Conclusions: Faced with the issue of the proliferation of websites with questionable quality content, and the fact that the ranking of results interferes directly in the internal evaluation of content relevance, we propose that public-health research institutions cooperate with web-searching developers to improve the website-positioning formula, in which the “identified authorship” criterion should play a major role in the ranking system.

Behind HumanBoost: Analysis of Users’ Trust Decision Patterns for Identifying Fraudulent Websites

This paper analyzes users’ trust decision patterns for detecting phishing sites. Our previous work proposed HumanBoost [1] which improves the accuracy of detecting phishing sites by using users’ Past Trust Decisions (PTDs). Web users are generally required to make trust decisions whenever their personal information is requested by a website. Human-Boostassumed that a database of Web user’s PTD would be transformed into a binary vector, representing phishing or not-phishing, and the binary vector can be used for detecting phishing sites, similar to the existing heuristics. Here, this paper explores the types of the users whose PTDs are useful by running a subject experiment, where 309 participants- browsed 40 websites, judged whether the site appeared to be a phishing site, and described the criterion while assessing the credibility of the site. Based on the result of the experiment, this paper classifies the participants into eight groups by clustering approach and evaluates the detection accuracy for each group. It then clarifies the types of the users who can make suitable trust decisions for HumanBoost.

Evaluation of the Websites of Logistics Operators by Customers

In this article, the results were presented of research concerning the visual and functional aspects of the websites of three largest logistics operators in Poland. The research was carried out with the participation of the following three groups： institutional customers, individual customers and marketing management students. The article covers an attempt to evaluate cooperation through virtual contacts with the company. The analysis also concerned such issues as information on corporate social responsibility （CSR）, information on job offers and the position of the company on the market.

A Study on C-E Translation of Product Introductory Texts on Company Websites Under Skopos Theory

This paper takes the C-E translation of product introductory texts on official websites of three mobile phone makers as the study object under the Skopos theory, with an aim to identify and analyze the distinctive translation features of such special type of text. The exhausted parse and analysis bring out the findings that there exists a significant translation difference between the Chinese and English-version product introductory texts on official websites. It is found that Chinese introductory texts are more inclined to rely on exquisite words and redundant expressions to describe products’ features and functions, while switching to the corresponding English version, simple vocabularies and compact sentence structure are more frequent. Hereafter, this paper raises two practical guidelines to instruct translation activities in business contexts.

Investigation and Analysis on Websites of Public Libraries in Jiangxi Province

This paper analyzes the significance of the library website establishment. On this basis, the author investigates the present situation of the websites of public library at and above the count3＇ level in Jiangxi province according the investigation： we point out the problems of the public library websites in Jiangxi province, and then give some corresponding measures.

Evaluation and Comparison Research on the Support of Websites to Enterprise's E-Commerce

This paper comparatively analyzes the existing evaluation index of websites, and puts forward the evaluation index and method about the support of a website to enterprise's e-commerce. Through researching on 56 super enterprises of information industry in Sichuan province, throughout China and the world, analyzing and comparatively studying the support ability of a website to an enterprise's e-commerce, this paper brings forward using five levels to categorize the support ability of a website to enterprise's e-commerce. In the end, the flaw of enterprise's e-commerce practice in Sichuan province and corresponding countermeasure will be illustrated.

Investigation and Analysis on Websites of Public Libraries in Jiangxi Province

This paper analyzes the significance of the library website establishment. On this basis, the author investigates the present situation of the websites of public library at and above the county level in Jiangxi province according the investigation; we point out the problems of the public library websites in Jiangxi province, and then give some corresponding measures.

Growth Model of Local Government Websites

To clarify the concept framework to assess web based information systems (WIS) evolution from an information perspective instead of the usual systems perspective, and to seek for in-depth understanding of maturing patterns of WISs based on the framework, several central concepts related to the information aspect of WIS are firstly discussed, then a growth model of local government websites based on a survey study is proposed.

Welcome to Visit the Websites of Partial Key Academic Journals from the Geological Society of China and the Chinese Academy of Geological Sciences

Publisher Acta Geologica Sinica-English Edition is published by Blackwell Publishing Asia Pty Ltd 155 Cremorne Street Richmond Vic.3121,Australia Tel:+61(0)3 9274 3100 Fax:+61(0)3 9274 3101

Websites

本期Functional Language，带您体验网页的相关表达……

Multimodal Fraudulent Website Identification Method Based on Heterogeneous Model Ensemble

The feature analysis of fraudulent websites is of great significance to the combat,prevention and control of telecom fraud crimes.Aiming to address the shortcomings of existing analytical approaches,i.e.single dimension and venerability to anti-reconnaissance,this paper adopts the Stacking,the ensemble learning algorithm,combines multiple modalities such as text,image and URL,and proposes a multimodal fraudulent website identification method by ensembling heterogeneous models.Crossvalidation is first used in the training of multiple largely different base classifiers that are strong in learning,such as BERT model,residual neural network(ResNet)and logistic regression model.Classification of the text,image and URL features are then performed respectively.The results of the base classifiers are taken as the input of the meta-classifier,and the output of which is eventually used as the final identification.The study indicates that the fusion method is more effective in identifying fraudulent websites than the single-modal method,and the recall is increased by at least 1%.In addition,the deployment of the algorithm to the real Internet environment shows the improvement of the identification accuracy by at least 1.9%compared with other fusion methods.