User Access Patterns Research Articles

TSAPP: Threshold Single-Sign-On Authentication Preserving Privacy

Single-sign-on (SSO) authentication enables a user to gain a token from the identity server, with which the user accesses multiple services. To address single-point-of-failure of SSO, threshold SSO, where a group of identity servers issue a user with a token in the threshold manner, is introduced. SSO including threshold schemes suffers from privacy disclosure. One can learn a user's identity and access pattern from her/his token. Recent works focus on privacy preservation of SSO. However, these works merely consider scenarios of one single identity server SSO. No works that address privacy preservation of threshold SSO have emerged. In this work, we propose TSAPP, a threshold SSO authentication scheme preserving privacy. Each identity server issues a user with a partial token which is a signature on the user's pseudonym. With a threshold number of partial tokens, the user constructs a token, blinds the token with random numbers and accesses services with blinded tokens. Such mechanism preserves the user's identity, simultaneously protects the user's access pattern since adversaries cannot link the user's accesses, even if identity servers are corrupted. Security analysis demonstrates that TSAPP satisfies properties of anonymity, unlinkability, unforgeability and password-safety. The performance evaluation demonstrates that TSAPP is efficient in practice.

Robots still outnumber humans in web archives in 2019, but less than in 2015 and 2012

The significance of the web and the crucial role of web archives in its preservation highlight the necessity of understanding how users, both human and robot, access web archive content, and how best to satisfy this disparate needs of both types of users. To identify robots and humans in web archives and analyze their respective access patterns, we used the Internet Archive’s (IA) Wayback Machine access logs from 2012, 2015, and 2019, as well as Arquivo.pt’s (Portuguese Web Archive) access logs from 2019. We identified user sessions in the access logs and classified those sessions as human or robot based on their browsing behavior. To better understand how users navigate through the web archives, we evaluated these sessions to discover user access patterns. Based on the two archives and between the three years of IA access logs (2012 vs. 2015 vs. 2019), we present a comparison of detected robots vs. humans and their user access patterns and temporal preferences. The total number of robots detected in IA 2012 (91% of requests) and IA 2015 (88% of requests) is greater than in IA 2019 (70% of requests). Robots account for 98% of requests in Arquivo.pt (2019). We found that the robots are almost entirely limited to “Dip” and “Skim” access patterns in IA 2012 and 2015, but exhibit all the patterns and their combinations in IA 2019. Both humans and robots show a preference for web pages archived in the near past.

Attribute-based Single Sign-On: Secure, Private, and Efficient

A Single Sign-On (SSO) system allows users to access different remote services while authenticating only once. SSO can greatly improve the usability and security of online activities by dispensing with the need to securely remember or store tens or hundreds of authentication secrets. On the downside, today's SSO providers can track users' online behavior, and collect personal data that service providers want to see asserted before letting a user access their resources. In this work, we propose a new policy-based Single Sign-On service, i.e., a system that produces access tokens that are conditioned on the user's attributes fulfilling a specified policy. Our solution is based on multi-party computation and threshold cryptography, and generates access tokens of standardized format. The central idea is to distribute the role of the SSO provider among several entities, in order to shield user attributes and access patterns from each individual entity. We provide a formal security model and analysis in the Universal Composability framework, against proactive adversaries. Our implementation and benchmarking show the practicality of our system for many real-world use cases.

Multi-keyword searchable encryption for smart grid edge computing

Searchable encryption scheme allows users to search for encrypted data containing some keywords without decrypting data. It protects the data privacy of data owners while promoting efficient data access. The searchable encryption scheme only supports a single keyword, which is easy to cause the problem of data redundancy. It makes users have to filter again in a large amount of data. In order to achieve the search goal more accurately, researchers proposed multi-keyword searchable encryption scheme. In addition, searchable encryption schemes that only support a single keyword are vulnerable to the disclosure of user access and search pattern. Based on these two reasons, we propose a searchable encryption scheme based on multi- keyword, which supports users to input more complex retrieval requests, and users can get a better sense of search experience. At the same time, it reduces the possibility of leakage of user access and search pattern to a certain extent. We also define the security model and prove that the scheme can resist the internal keyword guessing attack under the standard model. Finally, we also compare theoretical performance with other schemes and evaluate the experimental performance of our scheme.

A Review on Clustering Techniques: Creating Better User Experience for Online Roadshow

Online roadshow is a relatively new concept that has higher flexibility and scalability compared to the physical roadshow. This is because online roadshow is accessible through digital devices anywhere and anytime. In a physical roadshow, organizations can measure the effectiveness of the roadshow by interacting with the customers. However, organizations cannot monitor the effectiveness of the online roadshow by using the same method. A good user experience is important to increase the advertising effects on the online roadshow website. In web usage mining, clustering can discover user access patterns from the weblog. By applying a clustering technique, the online roadshow website can be further improved to provide a better user experience. This paper presents a review of clustering techniques used in web usage mining, namely the partition-based, hierarchical, density-based, and fuzzy clustering techniques. These clustering techniques are analyzed from three perspectives: their similarity measures, the evaluation metrics used to determine the optimality of the clusters, and the functional purpose of applying the techniques to improve the user experience of the website. By applying clustering techniques in different stages of the user activities in the online roadshow website, the advertising effectiveness of the website can be enhanced in terms of its affordance, flow, and interactivity.

Who Are Like-Minded: Mining User Interest Similarity in Online Social Networks

In this paper, we mine and learn to predict how similar a pair of users’ interests towards videos are, based on demographic, social and interest information of these users. We use the video access patterns of active users as ground truth. We adopt tag-based user profiling to establish this ground truth. We then show the effectiveness of the different features, and their combinations and derivatives, in predicting user interest similarity, based on different machine-learning methods for combining multiple features. We propose a hybrid tree-encoded linear model for combining the features, and show that it out-performs other linear and tree-based models. Our methods can be used to predict user interest similarity when the ground-truth is not available, e.g. for new users, or inactive users whose interests may have changed from old access data, and is useful for video recommendation.

Leveraging user access patterns and advanced cyberinfrastructure to accelerate data delivery from shared-use scientific observatories

With the growing number and increasing availability of shared-use instruments and observatories, observational data is becoming an essential part of application workflows and contributor to scientific discoveries in a range of disciplines. However, the corresponding growth in the number of users accessing these facilities coupled with the expansion in the scale and variety of the data, is making it challenging for these facilities to ensure their data can be accessed, integrated, and analyzed in a timely manner, and is resulting significant demands on their cyberinfrastructure (CI).In this paper, we present the design of a push-based data delivery framework that leverages emerging in-network capabilities, along with data pre-fetching techniques based on a hybrid data management model. Specifically, we analyze data access traces for two large-scale observatories, Ocean Observatories Initiative (OOI) and Geodetic Facility for the Advancement of Geoscience (GAGE), to identify typical user access patterns and to develop a model that can be used for data pre-fetching. Furthermore, we evaluate our data pre-fetching model and the proposed framework using a simulation of the Virtual Data Collaboratory (VDC) platform that provides in-network data staging and processing capabilities. The results demonstrate that the ability of the framework to significantly improve data delivery performance and reduce network traffic at the observatories’ facilities.

Research on Model and Algorithm of User Access Pattern Data Mining

The era of big data has come. Today, all kinds of information and data are showing explosive growth. Internet activities of different scales are struggling to catch up with the pace and pace of the development of "big data. This paper uses time series mining algorithms, and uses Microsoft's data mining tools to model the data sets collected from data halls, so as to discover the user's online behaviour patterns and potential online rules within a certain period of time. we made reasonable suggestions for the scientific management of the campus network. A new clustering method based on the improved Kohonen self-organizing feature mapping neural network is proposed. A Gaussian-shaped membership function has introduced to output several neurons with a degree of membership greater than the threshold, thereby solving the problem of mining users' multiple interests.

Toward QoS-Awareness and Improved Utilization of Spatial Multitasking GPUs

Datacenters use GPUs to provide the significant computing throughput required by emerging user-facing services. The diurnal user access pattern of user-facing services provides a strong incentive to co-located applications for better GPU utilization, and prior work has focused on enabling co-location on multicore processors and traditional non-preemptive GPUs. However, current GPUs are evolving towards spatial multitasking and introduce a new set of challenges to eliminate QoS violations. To address this open problem, we explore the underlying causes of QoS violation on spatial multitasking GPUs. In response to these causes, we propose C-Laius, a runtime system that carefully allocates the computation resource to co-located applications for maximizing the throughput of batch applications while guaranteeing the required QoS of user-facing services. C-Laius not only allows co-locating one user-facing application with multiple batch applications, but also supports the co-location of multiple user-facing applications with batch applications. In the case of a single co-located user-facing application, our evaluation on an Nvidia RTX 2080Ti GPU shows that C-Laius improves the utilization of spatial multitasking GPUs by 20.8 percent, while achieving the 99%-ile latency target for user-facing services. As to the case of multiple co-located user-facing applications, C-Laius ensures no violation of QoS while improving the accelerator utilization by 35.9 percent on average.

Exploiting temporal changes in query submission behavior for improving the search engine result cache performance

A commonly used technique for improving query response time in retrieval systems is storing query-relevant information in a fast access memory storage such as a result cache. The effectiveness of the result cache heavily relies on giving correct admission and eviction decisions, which require careful analysis of query and stream characteristics. Due to anonymous and global user access patterns, search engines are often considered time-invariant architectures: query characteristics are frequently collected globally, and assumed to be unchanging for long periods of time. However, the highly distributed nature of the modern search engine framework consequently led to noticeable temporal changes in user access patterns through short periods of time for each of the data center within the distributed network.The work presented here attempts to evaluate temporal variations in query submissions and exploit them in order to improve the result caching performance. To this end, query logs are analyzed in order to verify the availability of such variations and a new caching framework that facilitate these changes is proposed. The proposed framework partitions the result cache into three segments: a static segment that stores the most frequent queries in an offline fashion, a newly introduced semi-static segment on top of the state-of-the-art Static–Dynamic Cache (SDC) that changes content during different periods of the day, and a dynamic segment that is maintained in an Least Recently Used (LRU) fashion. Conducted experiments demonstrate that the proposed caching framework improves the hit rate of a search engine result cache up to 3.31% and query response time up to 7.27% with respect to the state-of-the-art techniques.

Using data mining techniques to predict user’s behavior and create recommender systems in the libraries and information centers

PurposeThis study aims to analyze and predict a user’s behavior and create recommender systems in libraries and information centers, using data mining techniques.Design/methodology/approachThe present study is an analytical survey study of cross-sectional type. The required data for this study were collected from the transactions of the users of libraries and information centers in Hamadan University of Medical Sciences. Using data mining techniques, the existing patterns were investigated, and users’ loan transactions were analyzed.FindingsThe findings showed that the association rules with the degree of confidence above 0.50 were able to determine user access patterns. Furthermore, among the decision tree algorithms, the C.05 predicted the loan period, referrals and users’ delay with the highest accuracy (i.e. 90.1). The other findings on feedforward neural network with R = 0.99 showed that the predicted results of neural network computation were very close to the real situation and had a proper estimation of user’s delay prediction. Finally, the clustering technique with the k-means algorithm predicted users’ behavior model regarding their loyalty.Practical implicationsThe results of this study can lead to providing effective services and improve the quality of interaction between librarians and users and provide a good opportunity for managers to align supply of information resources with the real needs of users.Originality/valueThe results of the study showed that various data mining techniques are applicable with high efficiency and accuracy in analyzing library and information centers data and can be used to predict a user’s behavior and create recommendation systems.

Research on User Access Pattern Mining Based on Web Log

Research on User Access Pattern Mining Based on Web Log

Research on Clustering Algorithm Based on Web Log Mining

People’s online business behaviour has become more and more frequent. Internet service providers are beginning to find ways to obtain the interests and hobbies of users in order to provide targeted services to users. Analysis of user behavior based on Web logs can obtain valuable information from users. User clustering based on Web logs can cluster users according to user behavior, and then analyze user access patterns, providing a good solution for problem solving. This article introduces the concept and process of data mining, the classification and process of Web data mining, and then analyzes the K-Means clustering algorithm. The class-centered algorithm avoids clustering and only obtains the local optimal solution, and it can reduce the algorithm iteration time and improve the clustering quality.

GCRFP - PAGE REPLACEMENT FOR SOLID STATE DRIVE USING GHOST-CACHE

State Drive (SSD) is an alternative to data storage that is popular today, widely used as a media cache to speed up data access to the hard disk (HDD). This paper proposes page replacement technique on SSD cache that used frequency and recency parameter, alternately. The algorithm is selected adaptively based on trace input. This method helps to overcome changes in access patterns while minimizing the number of write processes to SSD. The proposed algorithm can choose a replacement technique that suits the user access pattern so that it can bring a better hit rate. The proposed algorithm is also integrated with the ghost-cache mechanism so that the reduction in the number of writing processes to SSD is significant. The experiment runs using a real dataset, describing trace of data read, and data write taken from real usage. The trial shows that the proposed algorithm can give good results compared to other similar algorithms.

AutoSight: Distributed Edge Caching in Short Video Network

In recent years there has been a rapid increase of short video traffic in CDN. While the video contributors change from large video studios to distributed ordinary end users, edge computing naturally matches the cache requirements from short video network. But distributed edge caching exposes some unique characteristics: non-stationary user access pattern and temporal and spatial video popularity pattern, which severely challenge the edge caching performance. While the QoE in traditional CDN has been much improved, prior solutions become invalid in solving the above challenges. In this article, we present AutoSight, a distributed edge caching system for short video network, which significantly boosts cache performance. AutoSight consists of two main components, solving the above two challenges respectively: the CoStore predictor, which solves the non-stationary and unpredictability of local access pattern, by analyzing the complex video correlations; and a caching engine Viewfinder, which solves the temporal and spatial video popularity problem by automatically adjusting future horizon according to video life span. All these inspirations and experiments are based on the real traces of more than 28 million videos with 100 million accesses from 488 servers located in 33 cities. Experiment results show that AutoSight brings significant boosts on distributed edge caching in short video network.

FedORAM: A Federated Oblivious RAM Scheme

Instant messaging (IM) applications, even with end-to-end encryption enabled, pose privacy issues due to metadata and pattern leakage. Our goal is to develop a model for a privacy preserving IM application, by designing an IM application that focuses on hiding metadata and discussion patterns. To solve the issue of privacy preservation through the obfuscation of metadata, cryptographic constructions like Oblivious Random Access Machines (ORAM) have been proposed in recent years. However, although they completely hide the user access patterns, they incur high computational costs, often resulting in excessively slow performance in practice. We propose a new federated model, FedORAM, which is the first ORAM scheme that uses a federation of servers to hide metadata for an IM use case. In order to investigate the trade-off between security and performance, we propose two versions of FedORAM: Weak FedORAM and Strong FedORAM. Strong FedORAM uses a tree-based federation architecture to ensure strong obliviousness, but with an increased overhead cost. Weak FedORAM has a more simple federated architecture that only uses Oblivious Transfer (OT) to increase communication speed, but with security consequences. Our results show that both constructions are faster than a similar client-server ORAM scheme. Furthermore, Weak FedORAM has a response time of less than 2 seconds per message for a middle-sized federation.

Research Aligned Analysis on Web Access Behavioral Pattern Mining for User Identification

Human activity understanding includes activity recognition and activity pattern discovery. Monitoring human activity and finding abnormality in their activities used by many field like medical applications, security systems etc. Basically it helps and support in decision making systems. Mining user activity from web logs can helps in finding hidden information about the user access pattern which reveals the web access behaviour of the users. Clustering and Classification techniques are used for web user identification. Clustering is the task of grouping similar patterns for web user identification. Classification is the process of classifying web patterns for user identification. In this paper we have implemented the existing works and discussed the results here to find the limitations. In existing methods, many data mining techniques were introduced for web user behaviour identification. But, the user identification accuracy was not improved and time consumption was not reduced. Our objective is to study the existing work and explore the possibility to improve the identification accuracy and reduce the time consumption using machine learning and deep learning techniques.

Global and local scaling analysis of link streams in access and backbone core networks

Due to continuous innovations in links and their flows traditional Internet traffic analysis with novel applications will always remain an active area of research. These innovations in links are due to dynamic user access patterns, end point software applications, carrier media, flow interactions, muliplexing, demultiplexing and data center access, for example. This article presents a new framework for analysis of Internet traffic based on formalism of Link Streams which is better than traditional graph theory in terms of uncovering temporal but converged dependence structures in various traffic components and their aggregates. This article is the first study which presents a joint global and local scaling analysis of direction tagged traffic originating and terminating at three different Internet access links belonging to DSL, Ethernet and Wifi hotspot networks and their backbone core network. The notion of link streams has encouraged us to assess Internet traffic both in terms of dynamics of link components along with their sub components like packets, flows and sessions with their aggregates. Link stream based analysis framework has led us to develop simple and realistic Internet traffic models based on Weibull and superposed Pareto renewal processes which capture both global and local scaling properties of Internet traffic in terms of their interactions in access and backbone core networks.

Practical Suitability and Experimental Assessment of Tree ORAMs

Oblivious Random-Access Memory (ORAM) is becoming a fundamental component for modern outsourced storages as a cryptographic primitive to prevent information leakage from a user access pattern. The major obstacle to its proliferation has been its significant bandwidth overhead. Recently, several works proposed acceptable low-overhead constructions, but unfortunately they are only evaluated using algorithmic complexities which hide valuable constants that severely impact their practicality. Four of the most promising constructions are Path ORAM, Ring ORAM, XOR Ring ORAM, and Onion ORAM. However, they have never been thoroughly compared against each other and tested on the same experimental platform. To address this issue, we provide a thorough study and assessment of these recent ORAM constructions and implement them under the same testbed. We perform extensive experiments to provide insights into their performance characteristics, simplicity, and practicality in terms of processing time, server storage, client storage, and communication cost. Our extensive experiments show that despite the claimed algorithmic efficiency of Ring and Onion ORAMs and their judicious limited bandwidth requirements, Path ORAM stands out to be the simplest and most efficient ORAM construction.

Significance of Hierarchical and Markov Clustering in Grouping Aware Data Placement for Data Intensive Applications Having Interest Locality

In this data era, massive volumes of data are being generated every second in variety of domains such as Geoscience, Social Web, Finance, e-Commerce, Health Care, Climate modelling, Physics, Astronomy, Government sectors etc. Hadoop has been well-recognized as de factobig data processing platform that have been extensively adopted, and is currently widely used, in many application domains processing Big Data. Even though it is considered as an efficient solution for such complex query processing, it has its own limitation when the data to be processed exhibit interest locality. The data required for any query execution follows grouping behavior wherein only a part of the Big-Data is accessed frequently. During such scenarion, the time taken to execute a queryand return results, increases exponentially as the amount of data increases leading to much waiting time for the user. Since Hadoop default data placement strategy (HDDPS) does not consider such grouping behavior, it does not perform efficiently resulting in lacunas such as decreased local map task execution, increased query execution time etc. Hence proposed an Optimal Data Placement Strategy (ODPS) based on grouping semantics. In this paper we experiment the significance oftwo most promising clustering techniques viz. Hierarchical Agglomerative Clustering (HAC) and Markov Clustering (MCL) in grouping aware data placement for data intensive applications having interest locality. Initially user access pattern is identified by dynamically analyzing history log.Then both clustering techniques (HAC & MCL) are separately applied over the access pattern to obtain independent clusters. These clusters are interpreted and validated to extract the Optimal Data Groupings (ODG). Finally proposed strategy reorganizes the default data layouts in HDFSbased on ODG to achieve maximum parallel execution per group subjective to Load Balancer and Rack Awareness. Our proposed strategy is tested in 10 node cluster placed in a multi rack with Hadoop installed in every node deployed in cloud platform. Proposed strategy reduces the query execution time, significantly improves the data locality and has proved to be more efficient for massive datasets processing in heterogeneous distributed environment. Also MCL shows a marginal improved performance over HAC for queries exhibiting interest localities.