User Access Behavior Research Articles

BERT4Cache: a bidirectional encoder representations for data prefetching in cache.

Cache plays a crucial role in improving system response time, alleviating server pressure, and achieving load balancing in various aspects of modern information systems. The data prefetch and cache replacement algorithms are significant factors influencing caching performance. Due to the inability to learn user interests and preferences accurately, existing rule-based and data mining caching algorithms fail to capture the unique features of the user access behavior sequence, resulting in low cache hit rates. In this article, we introduce BERT4Cache, an end-to-end bidirectional Transformer model with attention for data prefetch in cache. BERT4Cache enhances cache hit rates and ultimately improves cache performance by predicting the user's imminent future requested objects and prefetching them into the cache. In our thorough experiments, we show that BERT4Cache achieves superior results in hit rates and other metrics compared to generic reactive and advanced proactive caching strategies.

An electronic medical record access control model based on intuitionistic fuzzy trust

Electronic Medical Records (EMR), as the core data of medical big data, has improved the efficiency of medical services in the process of sharing and use, but a series of data privacy leakage problems have emerged. Access control technology can ensure users' legitimate and appropriate access to data resources, but traditional access control has many limitations such as static and coarse-grained, which is difficult to meet in the dynamic and complex healthcare environment. We create a model to solve the privacy leakage problem of healthcare big data. The model utilizes the Latent Delicacy Allocation (LDA) topic model to quickly search documents and extract the topic probability distributions between the target patient and other patients' electronic medical records, which improves the efficiency of medical record document analysis; Calculating physician access similarity, we quantify physician access behavior to more accurately describe physician access behavior in the form of data. We combined the intuitionistic fuzzy theory with the trust evaluation method to create a novel trust evaluation method-- Intuitionistic Fuzzy Trust Evaluation Method, which can reflect the uncertainty characteristics that exist in the physician's diagnostic and treatment process when quantifying the trust of the access by using this method, and it is more flexible and practical, which enhances the accuracy of the quantification of the trust. Improving the traditional trust aggregation method by adding a time window and time decay function, the optimized method improves the accuracy of trust aggregation, and the experimental results are more in line with the actual law. We created a new intuitionistic fuzzy trust access control model using a relative entropy-based intuitionistic fuzzy clustering algorithm and a reward and punishment mechanism to achieve adaptive and dynamic access control for physician access behavior. Experiments show that the access control model based on intuitionistic fuzzy trust proposed in this article achieves 95% correctness in identifying user access behaviors and 94.29% correctness in identifying excessive user access behaviors. Experiments have proved that this model has obvious advantages over other models in the process of privacy protection of electronic medical record systems and has certain control effects.

DeepScraper: A complete and efficient tweet scraping method using authenticated multiprocessing

In this paper, we propose a scraping method for collecting tweets, which we call DeepScraper. DeepScraper provides the complete scraping for the entire tweets written by a certain group of users or them containing search keywords with a fast speed. To improve the crawling speed of DeepScraper, we devise a multiprocessing architecture while providing authentication to the multiple processes based on the simulation of the user access behavior to Twitter. This allows us to maximize the parallelism of crawling even in a single machine. Through extensive experiments, we show that DeepScraper can crawl the entire tweets of 99 users, which amounts to 5,798,052 tweets while Twitter standard API can crawl only 243,650 tweets of them due to the constraints of the number of tweets to scrape. In other words, DeepScraper could collect 23.7 times more tweets for the 99 users than the standard API. We also show the efficiency of DeepScraper. First, we show the effect of the authenticated multiprocessing by showing that it increases the crawling speed from 2.03∼10.57 times as the number of running processes increases from 2 to 32 compared to DeepScraper with a single process. Then, we compare the crawling speed of DeepScraper with the existing studies. The result shows that DeepScraper is compared to even Twitter standard APIs and Twitter4J while DeepScraper can scrape much more tweets than them. Furthermore, DeepScraper is much faster than Twitter Scrapy roughly 3.69 times while both can scrape the entire tweets for the target users or keywords.

A Dynamic and Fine-Grained User Trust Evaluation Model for Micro-Segmentation Cloud Computing Environment

<p>With the diversity and complexity of user access behaviors in the “micro-segmentation” cloud computing environment, it is no longer possible to control unauthorized access of authorized users by only relying on user identity login authentication to control user access to cloud resources. The existing trust evaluation methods can not cope with the characteristics of “micro-isolated” cloud environment, which is characterized by high granularity of resources, increasing number of users’ access requests and rapid changes. Based on the zero-trust principle of “Never trust, al-ways verify”, we propose a dynamic, fine-grained user trust evaluation model for micro-segmentation cloud computing environment, which combines multiple user trust attributes and leverages the subjective-objective approach to assign weights to trust attribute indicators to achieve dynamic scoring of users’ real-time behaviors. To capture the characteristics of users’ intrinsic behaviors, we use correlation analysis to identify the correlation between users’ current and historical behaviors, and combine sliding windows and penalty functions to optimize the model. The massive simulation experiments demonstrate the effectiveness of the proposed dynamic and fine-grained method, which can effectively combine the intrinsic correlation of users’ own access behavior and the difference of access behavior among different users.</p> <p> </p>

RUMP: Resource Usage Multi-Step Prediction in Extreme Edge Computing

Extreme Edge Computing that leverages the copious yet underutilized computational resources of Extreme Edge Devices (EEDs) has gained significant momentum lately. Estimating the computational capabilities of EEDs can be strenuously challenging since EEDs are user-owned devices, and are thus subject to a highly dynamic user access behavior (i.e., dynamic resource usage). In this paper, we propose the Resource Usage Multi-step Prediction (RUMP) scheme. RUMP is the first scheme that strives to enable multistep-ahead prediction of the dynamic resource usage of EEDs (i.e., workers) in a computationally efficient way, while providing a relatively high prediction accuracy. Towards that end, RUMP exploits the use of the Hierarchical Dirichlet Process-Hidden Semi-Markov Model (HDP-HSMM). In addition, RUMP uses the Simple and Exponential Moving Average (SMA&EMA) and Savitzky-Golay (SG) filters to improve the prediction accuracy. We scrupulously study the trade-off between computational efficiency, prediction accuracy, practicality, and adaptability of the underlying prediction model by conducting complexity analysis, performing various experiments on a testbed of heterogeneous workers, and comparing the HDP-HSMM model used in RUMP to three other prominent prediction models in different dynamic resource usage scenarios. Extensive evaluations show that RUMP achieves a 91% categorical multi-step prediction accuracy and renders a small performance gap of 6% on average in terms of the Mean Absolute Error (MAE) compared to representatives of state-of-the-art prediction models, while yielding a low computational complexity.

Access control scheme based on blockchain and attribute-based searchable encryption in cloud environment

With the rapid development of cloud computing technology, how to achieve secure access to cloud data has become a current research hotspot. Attribute-based encryption technology provides the feasibility to achieve the above goal. However, most of the existing solutions have high computational and trust costs. Furthermore, the fairness of access authorization and the security of data search can be difficult to guarantee. To address these issues, we propose a novel access control scheme based on blockchain and attribute-based searchable encryption in cloud environment. The proposed scheme achieves fine-grained access control with low computation consumption by implementing proxy encryption and decryption, while supporting policy hiding and attribute revocation. The encrypted file is stored in the IPFS and the metadata ciphertext is stored on the blockchain, which ensures data integrity and confidentiality. Simultaneously, the scheme enables the secure search of ciphertext keyword in an open and transparent blockchain environment. Additionally, an audit contract is designed to constrain user access behavior to dynamically manage access authorization. Security analysis proves that our scheme is resistant to chosen-plaintext attacks and keyword-guessing attacks. Theoretical analysis and experimental results show that our scheme has high computational and storage efficiency, which is more advantageous than other schemes.

A fusion data security protection scheme for sensitive E-documents in the open network environment.

E-documents are carriers of sensitive data, and their security in the open network environment has always been a common problem with the field of data security. Based on the use of encryption schemes to construct secure access control, this paper proposes a fusion data security protection scheme. This scheme realizes the safe storage of data and keys by designing a hybrid symmetric encryption algorithm, a data security deletion algorithm, and a key separation storage method. The scheme also uses file filter driver technology to design a user operation state monitoring method to realize real-time monitoring of user access behavior. In addition, this paper designs and implements a prototype system. Through the verification and analysis of its usability and security, it is proved that the solution can meet the data security protection requirements of sensitive E-documents in the open network environment.

Deep-Learning-Enhanced NOMA Transceiver Design for Massive MTC: Challenges, State of the Art, and Future Directions

Non-orthogonal multiple access (NOMA) is a promising evolution path to meet the requirements of massive machine type communications (mMTC) in 5G and beyond. However, the deployment of NOMA is hindered by the non-unified signal processing architectures of various NOMA schemes and the inflexibility resulting from the offline design paradigm. The block-wise optimized transceivers make its performance far from the limit. The recent breakthrough of deep learning and its positive applications to wireless communications have paved the way to tackle these challenges. This article studies the effectiveness and efficiency of deep learning in enhancing NOMA performance. Specifically, we first present the deep neural network (DNN), which is constructed via a uniform signal processing architecture, and use it as the unified multiuser receiver in both data and model-driven approaches. This enables the end-to-end optimization of NOMA transceivers due to the universal function approximation property of DNN. On the other hand, with DNN we can automatically extract the user access behaviors out of the time-series signals and optimize the transceivers to match these cross-lay-er behaviors. We further analyze the integration of non-orthogonal communication and neural computation to accomplish high-efficiency data transmission at low cost. Finally, we identify some essential future directions of deep-learning-enhanced NOMA from the perspectives of online reconfigurability and adaptability toward the ever changing environment in future mMTC.

Research on lightweight web intrusion active defense key technology and visual measurement model based on dynamic ip black list

In view of the existing passive detection and prevention methods and lack of commercial products are expensive and complex deployment problem of a simple and fast active defense technology of WEB dynamic real-time active defense, in order to solve the problem of attack and defense for WEB server. Firstly, based on reverse proxy massive WAF logs, the mathematical model of user access behavior is established, and the behavior characteristics of malicious WEB attacks are studied through data mining analysis. Then, a threat factor algorithm and a dynamic IP blacklist generation algorithm are designed based on these features and a custom rule base. Finally, based on visual measurement model, D3 WEB visualization technology is used to monitor and measure WEB intrusion. The technology reduces the false alarm and false positive rate of active defense, improves the defense effect and execution efficiency, and ensures the quality of normal network communication.

A Privacy Risk Assessment Model for Medical Big Data Based on Adaptive Neuro-Fuzzy Theory

Information leakage in the medical industry has become an urgent problem to be solved in the field of Internet security. However, due to the need for automated or semiautomated authorization management for privacy protection in the big data environment, the traditional privacy protection model cannot adapt to this complex open environment. Although some scholars have studied the risk assessment model of privacy disclosure in the medical big data environment, it is still in the initial stage of exploration. This paper analyzes the key indicators that affect medical big data security and privacy leakage, including user access behavior and trust, from the perspective of users through literature review and expert consultation. Also, based on the user’s historical access information and interaction records, the user’s access behavior and trust are quantified with the help of information entropy and probability, and a definition expression is given explicitly. Finally, the entire experimental process and specific operations are introduced in three aspects: the experimental environment, the experimental data, and the experimental process, and then, the predicted results of the model are compared with the actual output through the 10-fold cross verification with Matlab. The results prove that the model in this paper is feasible. In addition, the method in this paper is compared with the current more classical medical big data risk assessment model, and the results show that when the proportion of illegal users is less than 15%, the model in this paper is more superior in terms of accuracy and recall.

Personalized E-commerce Website Construction Based on Data Mining

With the development of supply chain and logistics, e-commerce system can provide a growing variety of goods and quantity. The traditional website-centered retrieval business model has become a bottleneck restricting the value-added of e-commerce enterprises. Data mining technology enables people to finally understand the real value of data, that is, the information and knowledge contained in the data. For e-commerce enterprises, rich data sources and reliable data collected automatically make it easy to meet the necessary factors of data mining. Web server logs contain a large number of records of users accessing e-commerce systems, and data mining technology is used to process and analyze the data. Create a convenient, fast and personalized e-commerce website to provide a reliable analysis basis for the market positioning, strategy improvement, customer relationship improvement and service quality improvement, so as to improve the competition of enterprises in the market. Force to create better benefits. Through data mining, the analysis of user access behavior, frequency, content, etc., can extract the description characteristics of each user, so as to obtain knowledge about the behavior and manner of group user access.

Identifying Application-Layer DDoS Attacks Based on Request Rhythm Matrices

Application-layer distributed denial of service (AL-DDoS) attacks are becoming critical threats to websites because the stealth of AL-DDoS attacks makes many intrusion prevention systems ineffective. To detect AL-DDoS attacks aimed at websites, we propose a novel statistical model called the RM (rhythm matrix). Although the original features from the network layer are adopted, the access trajectory, including requested objects and corresponding dwell-time values, can be abstracted and accumulated into an RM. With an RM, we can almost losslessly compress complex features into a simple structure and characterize the user access behavior. We detect AL-DDoS attacks according to the increase of the abnormality degree in the RM and further identify malicious hosts based on change-rate outliers. In the experiments, we simulate three modes of AL-DDoS attacks with the latest popular DDoS attack tools: LOIC and HOIC. The results show that our method can detect these simulated attacks and identify the malicious hosts accurately and efficiently. For an AL-DDoS detection method, the ability to distinguish flash crowds is indispensable. We also demonstrate the excellent performance of our approach in distinguishing flash crowds from AL-DDoS attacks with two reconstructed public datasets.

A software defined caching framework based on user access behavior analysis for transparent computing server

A large number of resource access requests from heterogeneous terminals bring severe challenges to ensuring the performance and efficiency of Tranparent Computing server. Caching mechanism plays a significant role in performance improvement of transparent computing systems. Nevertheless, the existing caching mechanisms do not take into account the complex and volatile runtime context in the server-side, such as the change in users’ access requirements for the resources and server performance status, so that their cache scheduling strategies are lack of flexibility and diversity.Thus, in this paper, we proposed a software defined cache scheduling framework that can dynamically and flexibly schedule appropriate caching policies according to the monitored information to achieve optimal caching performance for transparent computing server. First, we constructed a multi-layer and linked virtual disk storage model and its resource access mechanism. Then, based on this storage model, in order to perceive changes in the users’ demand for server resources, we adopted information entropy to model and analyze the user access behavior, and predict it with exponential smoothing algorithm. Finally, the cache scheduling is defined as an optimization problem from two aspects of prefetching and replacement, and some heuristic algorithms are used to obtain the approximate optimal solutions based on the conclusions of user access behavior analysis and prediction. We made experiments on the real data and tested the effectiveness of our approach, and the results show that our approach can achieve better caching performance than traditional methods, thus improving the service quality and user experience of transparent computing effectively.

A Reinforcement-Learning Approach to Proactive Caching in Wireless Networks

We consider a mobile user accessing contents in a dynamic environment, where new contents are generated over time (by the user’s contacts) and remain relevant to the user for random lifetimes. The user, equipped with a finite-capacity cache memory, randomly accesses the system and requests all the relevant contents at the time of access. The system incurs an energy cost associated with the number of contents downloaded and the channel quality at that time. Assuming causal knowledge of the channel quality, the content profile, and the user-access behavior, we model the proactive caching problem as a Markov decision process with the goal of minimizing the long-term average energy cost. We first prove the optimality of a threshold-based proactive caching scheme, which dynamically caches or removes appropriate contents from the memory, prior to being requested by the user, depending on the channel state. The optimal threshold values depend on the system state and hence are computationally intractable. Therefore, we propose parametric representations for the threshold values and use reinforcement-learning algorithms to find near-optimal parameterizations. We demonstrate through simulations that the proposed schemes significantly outperform classical reactive downloading and perform very close to a genie-aided lower bound.

Mining web access patterns with super-pattern constraint

We consider the problem of mining web access patterns with super-pattern constraint. This constraint requires that the sequential patterns in the sequence database must contain a particular set of patterns as sub-patterns. One common application of this constraint is web usage mining which mines the user access behavior on the web. In this paper, we introduce an efficient strategy for mining web access patterns with super-pattern constraint that requires only one database scan. Firstly, we present the MWAPC (M ining W eb A ccess P atterns based on super-pattern C onstraint) algorithm, in which each frequent pattern has to be checked if it contains at least one pattern from a user-defined set of patterns. Then we develop an effective algorithm, called EMWAPC that prunes the search space at the beginning of mining process and avoids checking the constraints one by one based on three proposed propositions. We have conducted the experiments on real web log databases. The experimental results show that the proposed algorithms outperform the previous methods.

Secure Software Rollback System

Users can utilize powerful computing resources in cloud computing, which brings users great convenience. However, cloud computing is also facing many challenges for data security as the users outsource their sensitive data to clouds, which are generally beyond the same trusted domain as data owners. To address this problem, access control, which grants access permissions to an authorized user, is considered as one of critical security mechanisms for data protection in cloud computing environment. However, due to the unpredictability of user identities and access behavior, access control in cloud computing has become a key security problem. In this project, we propose a self-adaptive access control model based on secure cloud computing environment. The secure cloud computing environment includes analyzer Engine, Detection Engine, Rollback Engine, execute parts and knowledge base, and the knowledge base is used to make decisions on access requests. We also propose our own algorithm to create the Secure Engine. The self-adaptive access control model based on Secure Cloud Computing Environment we proposed can be applied to cloud computing environment.

Replication Strategy for Spatiotemporal Data Based on Distributed Caching System.

The replica strategy in distributed cache can effectively reduce user access delay and improve system performance. However, developing a replica strategy suitable for varied application scenarios is still quite challenging, owing to differences in user access behavior and preferences. In this paper, a replication strategy for spatiotemporal data (RSSD) based on a distributed caching system is proposed. By taking advantage of the spatiotemporal locality and correlation of user access, RSSD mines high popularity and associated files from historical user access information, and then generates replicas and selects appropriate cache node for placement. Experimental results show that the RSSD algorithm is simple and efficient, and succeeds in significantly reducing user access delay.

Research on Improved Algorithm of PageRank Based on Vector Space

The traditional PageRank algorithm, which is based on the link analysis algorithm, considers the randomness of user access behavior, but the relevance of the query topic is poor. In order to improve the relevance of the page data search and acquisition, this paper proposes a PageRank algorithm based on the lucent vector space scoring model. The algorithm builds a vector space model based on the web content characteristics, calculates the similarity of the subject content, and combines the original PageRank algorithm, the new PR value is obtained after weighted fusion. Experiments show that the improved algorithm reduces the number of irrelevant pages, and the PR value can better reflect the relevance of the topic.

A Global User-Driven Model for Tile Prefetching in Web Geographical Information Systems.

A web geographical information system is a typical service-intensive application. Tile prefetching and cache replacement can improve cache hit ratios by proactively fetching tiles from storage and replacing the appropriate tiles from the high-speed cache buffer without waiting for a client’s requests, which reduces disk latency and improves system access performance. Most popular prefetching strategies consider only the relative tile popularities to predict which tile should be prefetched or consider only a single individual user's access behavior to determine which neighbor tiles need to be prefetched. Some studies show that comprehensively considering all users’ access behaviors and all tiles’ relationships in the prediction process can achieve more significant improvements. Thus, this work proposes a new global user-driven model for tile prefetching and cache replacement. First, based on all users’ access behaviors, a type of expression method for tile correlation is designed and implemented. Then, a conditional prefetching probability can be computed based on the proposed correlation expression mode. Thus, some tiles to be prefetched can be found by computing and comparing the conditional prefetching probability from the uncached tiles set and, similarly, some replacement tiles can be found in the cache buffer according to multi-step prefetching. Finally, some experiments are provided comparing the proposed model with other global user-driven models, other single user-driven models, and other client-side prefetching strategies. The results show that the proposed model can achieve a prefetching hit rate in approximately 10.6% ~ 110.5% higher than the compared methods.

High Performance AAA Security for Cloud Computing in Hierarchical Model

In internet and text documents tons of vital information is available. This side-information is available in documents as beginning information, the links within the documents, useraccess behavior from internet logs, or different non-textual characteristics which are embedded into the text document. This side information is employed in document clustering of such documents bunch. This information can embody noisy information as well; therefore it's tough to use it with efficiency. Thus correct algorithms are needed to use such information in document clustering to avoid noise from the extracted clusters. We'd like a properly dominated ways to perform the mining method to optimize the benefits got from mistreatment of this side information. In this work, we are improving the planning of AAA algorithm to accommodate high security and efficiency of the system.