2,463 Hits in 8.4 sec

A closed sets based learning classifier for implicit authentication in web browsing

Diyé Dia, Giacomo Kahn, Fabien Labernia, Yannick Loiseau, Olivier Raynaud
2018 Discrete Applied Mathematics  
To take up this challenge, we introduce in this paper a closed set-based learning classifier.  ...  Moreover, to strengthen our analysis, we have designed and set up one model based on the naive Bayes classifier to be used as a reference statistical tool.  ...  Acknowledgments This research was partially supported by the European Union's "Fonds Européen de Développement Régional (FEDER)" program and the Auvergne-Rhône-Alpes region's call for projects S3-DIS4  ... 
doi:10.1016/j.dam.2018.11.016 fatcat:khs6i2o3irdbbauyd5eezdwyau

Using Closed Itemsets for Implicit User Authentication in Web Browsing

Olivier Coupelon, Diyé Dia, Fabien Labernia, Yannick Loiseau, Olivier Raynaud
2014 International Conference on Concept Lattices and their Applications  
In this paper, we propose a new model for implicit authentication of web users based on extraction of closed patterns.  ...  On a data set of web navigation connection logs of 3,000 users over a six-month period we follow the experimental protocol described in [1] to compute performance of our model.  ...  Models We propose an intuitive learning model architecture for user authentication. From a data set of web browsing logs we compute a set of own patterns for each user.  ... 
dblp:conf/cla/CoupelonDLLR14 fatcat:f2wczfumurfuli42uuhthngrxq

Designing an adaptive web-based learning system based on students' cognitive styles identified online

Jia-Jiunn Lo, Ya-Chen Chan, Shiou-Wen Yeh
2012 Computers & Education  
This study developed an adaptive web-based learning system focusing on students' cognitive styles. The system is composed of a student model and an adaptation model.  ...  The system then adaptively recommended learning content presented with a variety of content and interactive components through the adaptation model based on the student cognitive style identified in the  ...  We would also like to thank the anonymous reviewers for insightful comments on this paper.  ... 
doi:10.1016/j.compedu.2011.08.018 fatcat:n3towsq2sfbjjaaiz7pobyzypq

Machine Learning for Web Page Classification: A Survey

safae lassri, EL HABIB BENLAHMAR, Abderrahim TRAGHA
2019 International Journal of Information Science and Technology  
To exploit this data, a Web information retrieval system and a categorization of internet content based on the classification of web pages are essential.  ...  In this paper, we present the characteristics of web page classification, we produce a literature review by summarizing and evaluating all sources related to web page classification crawled automatically  ...  To classify a web page 𝑝 𝑖 , KNN calculates similarities between 𝑝 𝑖 and each web page in the training set. Then, it ranks web pages in the training set based on those similarities.  ... 
doaj:483a4b9f259046a29c57adc3021a50d0 fatcat:hdznsdeotnhwpgpuigi7iovhja

User profiling for the web

Miha Grcar, Dunja Mladenic, Marko Grobelnik
2006 Computer Science and Information Systems  
When the user profiling is used for personalization in the context of Web, we can talk about Web personalization.  ...  This paper addresses a problem of personalized information delivery related to the Web, that is based on user profiling. Different approaches to user profiling have been developed.  ...  However, requiring users to authenticate is inappropriate for Web browsing in general. Session identification and path completion.  ... 
doi:10.2298/csis0602001g fatcat:tqyypei3mbe2bgy5viplsdzzn4

ICS: Total Freedom in Manual Text Classification Supported by Unobtrusive Machine Learning

Andrea Esuli
2022 IEEE Access  
We present the Interactive Classification System (ICS), a web-based application that supports the activity of manual text classification.  ...  Our efficient implementation of the unobtrusive machine learning model combines various machine learning methods and technologies, such as hash-based feature mapping, random indexing, online learning,  ...  Being stateless, the web services, the web application, and the machine learning modules can run in multiple instances 2 The web service uses only a session token to manage user authentication. and on  ... 
doi:10.1109/access.2022.3184009 fatcat:ru63xa67l5chvk7fd6ct3vrcsm

Through-the-looking glass

Alexey Tolstikov, Mikhail Shakhray, Gleb Gusev, Pavel Serdyukov
2013 Proceedings of the 22nd ACM international conference on Conference on information & knowledge management - CIKM '13  
We conduct a large-scale study and evaluation of a rich set of search trail features in realistic settings and conclude that a deeper investigation of a users experience far beyond her click on the result  ...  With increasing popularity of browser toolbars, the challenge of employing user behavior data stored in their logs rises in its importance.  ...  This classifier assigns each second-level domain whose documents are represented in our data set of search trails with some topic chosen from among the topics of the categorized data base.  ... 
doi:10.1145/2505515.2507890 dblp:conf/cikm/TolstikovSGS13 fatcat:22l3nwyqsjd3vdcmfbztyze5dm

Collective intelligence within web video

Konstantinos Chorianopoulos
2013 Human-Centric Computing and Information Sciences  
The concept of simple signal processing of implicit user interactions within video could be applied to any type of Web video system (e.g., TV, desktop, tablet), in order to improve the user navigation  ...  We present a user-based approach for detecting interesting video segments through simple signal processing of users' collective interactions with the video player (e.g., seek/scrub, play, pause).  ...  Acknowledgements We are thankful to the participants of the user study, and to Markos Avlonitis, David Ayman Shamma, Ioannis Leftheriotis, and Chryssoula Gkonela for assisting in the implementation and  ... 
doi:10.1186/2192-1962-3-10 fatcat:a2gcswlfg5d4tjdrp4aw7pquhu

A Multi-Feature User Authentication Model Based on Mobile App Interactions

Yosef Ashibani, Qusay H. Mahmoud
2020 IEEE Access  
This paper presents a user authentication and identification method based on mobile application access patterns, and throughout the paper we use a smart home environment as a motivating scenario.  ...  Knowledge-based authentication approaches such as the use of passwords and personal identification numbers (PINs) are the most common ways of authenticating users.  ...  An anomaly-based detection system that monitors the actions of users, such as calls, SMSs and Web browsing on mobile phones, is presented in [8] .  ... 
doi:10.1109/access.2020.2996233 fatcat:n5i4ojewizbcxhmvjbbxforubu

Web robot detection techniques: overview and limitations

Derek Doran, Swapna S. Gokhale
2010 Data mining and knowledge discovery  
Finally, we discuss why the contemporary techniques fail to offer a general solution to the robot detection problem and propose a set of key ingredients necessary for strong Web robot detection.  ...  We propose a framework to classify the existing detection techniques into four categories based on their underlying detection philosophy.  ...  Detection by implicit human browsing behavior While a Web robot is capable of exhibiting human-like patterns in its traffic, it can still be captured by a turing test system that checks for behavior unique  ... 
doi:10.1007/s10618-010-0180-z fatcat:p5y2lsboafhjjc6yg2lntflyjq

Leveraging Battery Usage from Mobile Devices for Active Authentication

Jan Spooren, Davy Preuveneers, Wouter Joosen
2017 Mobile Information Systems  
We make use of a large data set of battery charge readings from real users and construct two computationally inexpensive machine learning classifiers to predict if a user session is authentic: the first  ...  one only based on the battery charge at a certain time of day; the second one predicts the authenticity of the user session when a previous, recent battery charge reading is available.  ...  The authors wish to thank the Device Analyzer team of the University of Cambridge and Alastair Beresford in particular for making the Device Analyzer Dataset available.  ... 
doi:10.1155/2017/1367064 fatcat:uutz3zgr3nc77k2wbvsx5vikme

Enhancing Keyword Suggestion of Web Search by Leveraging Microblog Data

Lin Li, Lu Qi, Fang Deng, Shengwu Xiong, Jingling Yuan
2016 Journal of Web Engineering  
Most of popular web-search engines provide possible query suggestions based on their query log data, which is a kind of implicit relevance based approach.  ...  However, for hot topic or event related search queries, users more like to browse the latest and newly appeared contents.  ...  Graph Based Rank Aggregation In the context of web search, most search users just browse top 10 or 20 results. The top ranked items are more likely clicked.  ... 
dblp:journals/jwe/LiQDXY16 fatcat:ge5fa3h5xjehjijzmg2ubxpyku

The GeoKnow Generator Workbench - An Integrated Tool Supporting the Linked Data Lifecycle for Enterprise Usage

Andreas Both, Matthias Wauer, Alejandra García-Rojas, Daniel Hladky, Jens Lehmann
2015 International Conference on Semantic Systems  
The GeoKnow Generator Workbench solves these problems by providing an integrated Web interface on top of an extensible solution for easy access to tools dedicated to certain Linked Data lifecycle phases  ...  Linked Data promises to make data integration easier for academic and industrial use.  ...  Interlinking / Fusing Manual revision/ Authoring Classifi-cation/ Enrichment Storage/ Querying Linked Data Lifecycle Quality Analysis Extraction Evolution / Repair Search/ Browsing/ Exploration • Authentication  ... 
dblp:conf/i-semantics/BothWGHL15 fatcat:ldajaby2ybbtvjl6yjdir5xtoi

User Authentication Based on Handwriting Analysis of Pen-Tablet Sensor Data Using Optimal Feature Selection Model

Nasima Begum, Md Azim Hossain Akash, Sayma Rahman, Jungpil Shin, Md Rashedul Islam, Md Ezharul Islam
2021 Future Internet  
Handwriting analysis is playing an important role in user authentication or online writer identification for more than a decade.  ...  Extracted features are then fed to the popular machine learning (ML) algorithms to generate a nonlinear classifier through training and testing phases.  ...  Acknowledgments: Special thanks to University of Asia Pacific for supporting to do research. Thanks to IEERD, University of Asia Pacific for supporting for research and publication fund.  ... 
doi:10.3390/fi13090231 fatcat:c3o64ijkrrfbhmlbm43i7bexvy

The Role of Eye Gaze in Security and Privacy Applications: Survey and Future HCI Research Directions

Christina Katsini, Yasmeen Abdrabou, George E. Raptis, Mohamed Khamis, Florian Alt
2020 Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems  
In particular, we canvassed the literature and classify the utility of gaze in security applications into a) authentication, b) privacy protection, and c) gaze monitoring during security critical tasks  ...  For the past 20 years, researchers have investigated the use of eye tracking in security applications. We present a holistic view on gaze-based security applications.  ...  ACKNOWLEDGEMENTS This work was supported, in part, by the Royal Society of Edinburgh (Award number 65040), and the Deutsche Forschungsgemeinschaft (DFG), Grants AL 1899/2-1 and 1899/4-1.  ... 
doi:10.1145/3313831.3376840 dblp:conf/chi/KatsiniARKA20 fatcat:4kpwskjpzzchdlobkpcns4ltmy
« Previous Showing results 1 — 15 out of 2,463 results