Unsupervised Behavior Evaluation Method in Trustworthy Network

From the perspective of human science, this paper uses natural science as the tools and methods to analyze student network behavior, considering providing college teaching and student management decision-making as the focal point and fundamental starting point. The utilization of authoritative and professional website Categories ODP, shows the students’ interest in the Internet more accurately. There are many dimensions such as the basic information of students, IP address information of students, the information of college departments, time, the owned domain name, the card information and so on, which analyze the student network behavior in diversified ways. The charts using statistical analysis tools ProClarity to display, combining with the inherent properties of the user, and analyzing the campus network user data, to find the specific modes and laws of the student network user’s behavior and form the valuable knowledge; to find the formation, existing features and changing regularity of the student network users’ behavior, and raise the standards of related resources allocation; to find the features and laws of the student net users’ behavior, analyze the psychological characteristics of students, and provide decision support for student management.

There are many abnormal user behavior in the enterprise network environment, how to monitor it effectively is a hot research hotspot. At present, the analysis of abnormal behavior is mainly through the means of traffic monitoring, but there is no precise definition and related research on the behavior of enterprise network users. Therefore, the paper propose a model to analyze the abnormal behavior of enterprise network users. First, the data from the monitoring log of enterprise network should be pre-processing and the user behavior are serializing; then, for each user behavior sequence in sequence databases, calculating the user behavior similarity and correlation coefficient in a week by the improved algorithm; finally, comparing the similarity and the correlation coefficient between users and finding the user abnormal behavior. In this paper, we use the model to verify the feasibility of the internal network of the company, and find out the user’s abnormal behavior.

Aiming at the data security problem of the system in the network environment, this paper uses the hidden Markov model to analyze the user's access behavior in the network system and identify the malicious user behavior. First, the behavior characteristics of network users are analyzed, and then according to the related characteristics of hidden Markov, the observation order symbol and hidden state in the model are determined, and the user's access behavior is mapped into a hidden Markov chain. We give detailed experiments to prove the feasibility of applying the hidden Markov model to network user behavior authentication, and compare with other methods to get the accuracy of the model.

We study the degradation in network performance caused by the selfish behavior of noncooperative network users. We consider a directed network in which each edge possesses a latency function describing the common latency incurred by all traffic on the edge as a function of the edge congestion. Given a rate of traffic between each pair of nodes in the network, we aspire toward an assignment of traffic to paths in which the sum of all travel times (the total latency) is minimized; however, in many settings network users are free to route their traffic in a selfish manner, without regard to the total latency. We therefore assume that each network user routes its traffic on the minimum-latency path available to it, given the network congestion caused by the other users. In general such a selfishly motivated assignment of traffic to paths (a Nash equilibrium) will not minimize the total latency; hence, selfish behavior carries the cost of decreased network performance. We quantify this degradation in network performance via the price of anarchy, defined as the worst possible ratio between the total latency of a Nash equilibrium and of a minimum-latency routing of the traffic.In this paper, we show that the underlying network topology plays no role in the determination of the price of anarchy. Specifically, we show that under weak hypotheses on the class of allowable edge latency functions, the worst-case ratio between the total latency of a Nash equilibrium and of a minimum-latency routing for any multicommodity flow network is achieved by a single-commodity instance on a set of parallel links. In the special case where the class of allowable latency functions includes all of the constant functions, we prove that a network with only two parallel links suffices to achieve the worst-possible ratio. Informally, these results imply that the inefficiency inherent in a flow at Nash equilibrium stems from the inability of selfish users to discern which of two competing routes is superior and not from the topological complexity arising from the diverse intersections of many paths belonging to different commoditie.Our proof techniques also give powerful methods for computing the price of anarchy with respect to an arbitrary class of latency functions. We apply these methods to function classes that have been well studied in the literature (such as degree-bounded polynomials and functions of the form $\ell(x) = (u—x)—1} that are used to model edges with capacity u), thereby achieving the first tight analyses of the price of anarchy for significant classes of latency functions outside the class of linear functions.

In the rapidly evolving cybersecurity landscape, proactive threat mitigation has become essential for protecting sensitive data and systems from increasingly sophisticated attacks. The paper explores a holistic approach to enhancing cybersecurity by merging data-driven insights with user-centric security practices. This study highlights the limitations of traditional reactive security measures and advocates for a shift towards a proactive strategy that anticipates and addresses potential threats before they materialize. The research emphasizes the importance of leveraging data analytics to gain actionable insights into potential vulnerabilities and emerging threats. By analyzing large datasets from network traffic, user behavior, and historical incidents, organizations can identify patterns and anomalies that signal potential risks. These data-driven insights enable the development of more effective threat detection systems and predictive models that enhance an organization’s ability to respond swiftly to evolving cyber threats. In addition to data analytics, the study underscores the significance of integrating user-centric security protocols. Traditional security measures often overlook the human element, which can be a critical factor in both the efficacy of security measures and the overall risk profile. User-centric protocols focus on enhancing user awareness, implementing tailored security training, and promoting best practices in cybersecurity. This approach ensures that security measures are not only technologically sound but also aligned with user behavior and needs, reducing the risk of human error and improving overall security posture. The research also discusses practical implementation strategies for combining data-driven insights with user-centric protocols, including the use of advanced analytics tools, continuous user education, and adaptive security frameworks. Case studies demonstrate the benefits of this integrated approach, such as improved threat detection rates, reduced incident response times, and enhanced overall security resilience. In conclusion, this study presents a comprehensive framework for proactive cyber threat mitigation, emphasizing the synergy between data-driven analytics and user-centric security practices as a robust strategy for safeguarding against modern cyber threats. Keywords: Cyber Threat, Proactive, Data-Driven, User-Centric, Security Protocols

Insider attack is a serious threat to enterprises, organizations and countries. It has become a widely studied topic in the field of information security. This paper mainly aims to effectively detect masqueraders by profiling user behaviors with keystroke and network traffic. The fly-time of digraph is employed to build users' keystroke behavior. User network behavior is modeled with statistic and text features that are extracted from network traffic. The K-Means classifier is used to classify network traffic, and different classification results are mapped to different user operations accordingly. Extensive experimental result shows that, in the case of users' keystroke models, the detection rate is achieved from 77% to 87.5% and the false alarm rate is 0.44 %. When we use network models, the detection rate is 100% with the false alarm rate as 0.05%. In conclusion, network traffic can describe user network behaviors precisely, while the detection rate of user keystroke behaviors suffers from the insufficient user input from keyboard. It is obvious that a certain masquerader detection mechanism which is based on specific user behaviors, cannot reach satisfied results since the corresponding data is insufficient in different scenarios. It is necessary to use both two type of behaviors for different scenarios to achieve a better detection result.

In WCDMA networks, most economic-based resource management algorithms only assumed that network users were obedient, that is, users only accepted the price declared by network, which is called as price acceptation mechanism. Many research issues argued that it is necessary to accommodate, if possible, to use self-interest behaviours of users to strengthen the technical architecture of network engineering. Thus, this paper explicitly considered the selfishness of users, investigated the price anticipation mechanism in WCDMA networks, in which users acted as price anticipators. By price anticipator it meant users anticipated the effect of their behaviours on the network resource allocation, and adopted strategy correspondingly. From the view point of game theory, we investigated equilibrium properties of the price anticipation mechanism in WCDMA networks, and, through two scenarios, illustrated the relationship between price anticipation mechanism and price acceptation mechanism from the viewpoint of network revenue. Finally, we drew the conclusion that, the network revenue generated in price anticipation mechanism was less than revenue generated in price acceptation mechanism, (the difference between those two mechanisms is called as “price as anarchy”), and the network revenue generated in those two mechanisms tends to be consistent, when the effect of individual user is negligible.

A deep understanding of spatial traffic patterns modeling is not only essential for both theory analysis and simulation estimation of cellular network's performance, but also can provide us insight on the energy efficient deployment of future network architecture. Since the user behavior in cellular network is affected by the environment, which leads to that the spatial traffic fluctuations exhibit an obvious non-uniform patterns. Existing spatial traffic models are based on ideal assumptions, and these models fail to depict the real spatial traffic distribution cases in the current mobile cellular network. In this paper, based on real data from a mobile network operator in one large city of China, “Truncated two-dimensional DCT (Discrete Cosine Transform)” model is proposed, which characterize the spatial traffic pattern more precisely. Furthermore, comparison of the modeling results has been illustrated among three typical regions: dense urban, urban and suburban, which shows that the parameters of model formula for these three regions are different.

Anomalous behaviors in social networks can lead to privacy leaks and the spread of false information. In this paper, we propose an anomalous behavior detection method based on optimized graph embedding representation. Specifically, the user behavior logs are first extracted into a social network user behavior temporal knowledge graph, based on which the graph embedding representation method is used to transform the network topology and temporal information in the user behavior knowledge graph into structural embedding vectors and temporal information embedding vectors, and the hybrid attention mechanism is used to merge the two types of vectors to obtain the final entity embedding to complete the prediction and complementation of the temporal knowledge graph of user behavior. We use graph neural networks, which use the temporal information of user behaviors as a time constraint and capture both user behavioral and semantic information. It converts the two parts of information into vectors for concatenation and linear transformation to obtain a comprehensive representation vector of the whole subgraph, as well as joint deep learning models to evaluate abnormal behavior. Finally, we perform experiments on the Yelp dataset to validate that our method achieves a 9.56% improvement in the F1-score.

This thesis introduces the status and methods of data mining, aiming at the Nantong University campus network users access data preprocessing analysis, using the K-means clustering algorithm combined with SQL Server 2008 and Visual Studio 2008 business intelligence project function for data mining analysis, and the mining experimental results are analyzed and studied. The research indicates that the campus network users of Internet time has a positiver relevance with the rate of student's failing grades and a negative correlation with getting schlolarship and CET4(College English Test 4) achievements. What's more, it not only has a positive effect on school leaders fully understand the behavioral characteristics of students and campus network users of campus network usage, timely feedback and guiding the students to form a good habit of learning, but also plays an important role in improving the campus network bandwidth, performance and application efficiency.

Response Efficiency Optimization of Data Cube Online Analysis for Network user's behavior

Cellular Data Network measurement and analysis has long been used to characterize Cellular Data Network usage and user behaviors, but with the rapid growing of all kinds of smart terminals and the varied applications on them, the amount of Cellular Data Network data has been growing exponentially. With respect to this challenge, a new management system for the data storage and query has been emerging. In this paper, we present our applied Hadoop-based system with Cellular Data Network flow upload and analyze components. It combines data uploading and CDR (Calling Detail Records) query with Map/Reduce framework and HDFS. It uses Map/Reduce framework to process the users' request, HDFS to manage the data flow files. Our system has the ability to upload and for the network manager to query the CDR more conveniently and reliable. More importantly, our system is applied to a real-world and has a good scalability, effectiveness and efficiency.

The purpose of this document is to highlight two strategies which increased feedbacks and stimulated the diffusion of information in social networks. Starting by an online survey, which assists searchers in understanding the behavior of social network users, to define the problem. The information received with this survey has been tested on validation by an analyze on the most popular type of posting on social networks. The results of this study provided two strategies as a solution for the problem of dissatisfaction among users of social networks and to increase feedbacks and diffusion of information on social network. One strategy is manual and is based on the type of publication and the second strategy is automatically and takes the concept of collaborative work in to account

With the rapid development of information technology and the widespread application of computer networks, data security issues have become increasingly prominent, especially in key industries such as finance and medical care, where the protection of sensitive data has become a top priority. In order to meet these challenges, this article proposes a data security protection system based on deep learning (DL) technology, which can monitor and identify potential security threats in real time and greatly enhance data security by automatically analyzing and learning network traffic, user behavior, and intrusion characteristics. The study uses a deep belief network to complete high-intensity protection of personal or corporate private data while automatically countering and reminding some network intrusion behaviors. The performance differences in data security of individuals or enterprises before and after the use of the protection system were compared through experiments. The results show that the new system can improve data security performance by about 54.6% in all aspects. The results show that the new security protection model based on DL technology not only improves detection accuracy and response speed but also effectively resists emerging threats, providing a more solid protection barrier for network data.

In the present paper, a call admission control scheme that can learn from the network environment and user behavior is developed for code division multiple access (CDMA) cellular networks that handle both voice and data services. The idea is built upon a novel learning control architecture with only a single module instead of two or three modules in adaptive critic designs (ACDs). The use of adaptive critic approach for call admission control in wireless cellular networks is new. The call admission controller can perform learning in real-time as well as in offline environments and the controller improves its performance as it gains more experience. Another important contribution in the present work is the choice of utility function for the present self-learning control approach which makes the present learning process much more efficient than existing learning control methods. The performance of our algorithm will be shown through computer simulation and compared with existing algorithms.