Network Security Defense Model and Simulation Analysis Based on Big Data

Network security is not only related to personal information security, but also to the information security of the whole country. The application of big data technology in network security analysis can not only maximize the data acquisition, storage and analysis capabilities of the network system itself, but also further reduce the storage cost of the network information itself, and provide an important security guarantee for data retrieval and traceability. In this paper, a new idea of network security situational awareness model is proposed, and an effective network security situational awareness model is found from the perspective of network data traffic characteristics. The experimental results show that the machine learning and data mining algorithm in this paper has high accuracy and timeliness in processing large data. This provides a new way of thinking for the research and processing of new problems brought by big data.

The popularity of the Internet makes the network develop rapidly. However, the network security threat is more complex and hidden. The traditional network security alarm system has the problems of low accuracy and low efficiency when dealing with huge redundant data. Therefore, the research comprehensively considers the network security problems, proposes a network security situational awareness model for asset information protection combined with knowledge graph, establishes an asset-based network security knowledge graph, utilizes attribute graphs to complete the network attack scenario discovery and network situational understanding, and verifies the effectiveness and superiority of the model. The experimental results show that the research-proposed model detects an average of 9706 attacks out of 10000 attacks. For 100 high-risk level attacks, the number of detections is higher than 98. The average correctness, recall, and false alarm rates of the research proposed model are 99.48%, 99.04%, and 0.86%, respectively. In addition, when the model is running, its maximum memory usage is only 22.67%, and the time to complete the attack detection at the same time is 258.4s, both of which are much lower than the comparison algorithms. Finally, the research-proposed model is able to effectively reflect the impact of attack events on the posture of asset nodes. The proposed cybersecurity situational awareness model is of great theoretical and practical significance for improving organizational cybersecurity, innovating cybersecurity solutions, and maintaining the security of asset information in the digital era.

The attack and defense model of network security based on game theory has developed into an effective network security model. It is a hot topic in the field of network and information security to use the idea of game theory to attack and defend the network security. This paper analyzes the general model of game theory in the field of security. This paper also analyzes the general model of network security attack and defense game. This paper also analyzes the game theory model of cryptographic protocol. This paper studies the existing network security methods based on game theory, reviews the development and evolution process and technical core of network security based on game theory, and compares the specificity of network security models based on game theory. Finally, the paper discusses the problems in the field of network security based on game theory, and tries to forecast its future development trend.

Nowadays, the digital transformation of agriculture puts forward higher requirements for network security. In response to the complex network traffic data and chaotic attack data cycles in the current agricultural network environment, it is difficult for the network security situation awareness methods to effectively extract network security situation elements and perceive network security status. Therefore, this paper proposes a fusion model-based agricultural network security situation awareness method, namely, MSCNN-ResNeXt-Transformer. Firstly, ResNeXt is improved by fusion model, using Multi-Scale Convolutional Neural Network (MSCNN) instead of a single scale convolution structure. This enables the agricultural network security situation awareness model in digital economy to comprehensively extract network security situational elements from multiple scales. The Efficient Channel Attention (ECA) mechanism is then employed to further refine and characterize the data processed by the improved ResNeXt. Finally, the Transformer is used to optimize the proposed model and improve the accuracy of agricultural network security situation awareness in digital economy. The experimental results show that the accuracy, recall and F1 of MSCNN-ResNeXt-Transformer on MOORE, KDDCUP99 and WSN-DS are significantly better than traditional models, providing effective technical support for agricultural digital security protection.

Cloud computing not only provides convenience for users, but also brings certain information security threats to users. How to effectively protect the user’s information security has become one of the core issues of network security. This paper analyzes the problems and reasons of network security in cloud computing environment, and points out the main ways to improve network security. This paper analyzes the network security problems in the cloud computing environment, and discusses the information security technology in the network. This paper studies the definition, characteristics, classification and core technology of cloud computing security, analyzes the security risk of cloud computing network, and puts forward the cloud computing network security model and security level evaluation method from different angles. Level experiment results show that the network security model in cloud environment is feasible, computing can fully meet the development requirements of the current network information age, and effectively standardize the network security operation environment. The results show that: in 2016, the number of articles related to cloud computing is at least 2653, and in 2020, the number of articles related to cloud computing is at most 6438.

This paper introduced the concept, the classification and the control principal of network behaviors,discussed the concept, composition and structure, and the behavior control of the controlled network system, then proposed the detection and control model of abnormal behavior in controlled network system. This model of abnormal behavior detection was designed by combining misuse and intrusion detection mechanism, and is the specific application of the research on network behavior and controlled theory, and it controls the network behaviors especially abnormal behaviors. The theory is the basis for establishing the dynamic controllable network security system. With the development of network and information technologies, it seems that the network size, the diversity of network equipment and the complexity of network topology structure are constantlyincreasing, which leads to the probability of security problems emergeis also increasing. However, the traditional network security measures cannot meet the needs of the actual complex network activities, the existing information network has an urgent need to propose a new theory or new method which can reflect the overall network security and behavior control states. As a kind of efficient, scientific and reasonable network security theory, the controlled network is the integration of existing network security technologies and measures, and the aim of it is to construct a controlled network and solve the network security problems(1).

Denial of Service (DOS) and (DDOS) Distributed Denial of Service attacks have become a major security threat to university campus network security since most of the students and teachers prepare online services such as enrolment, grading system, library etc. Therefore, the issue of network security has become a priority to university campus network management. Using online services in university network can be easily compromised. However, traditional security mechanisms approach such as Defense-In-Depth (DID) Model is outdated in today’s complex network and DID Model has been used as a primary cybersecurity defense model in the university campus network today. However, university administration should realize that Defense-In-Depth (DID) are playing an increasingly limited role in DOS/DDoS protection and this paper brings this fact to light. This paper presents that the Defense-In-Depth (DID) is not capable of defending complex and volatile DOS/DDOS attacks effectively. The test results were presented in this study in order to support our claim. The researchers established a Defense-In-Depth (DID) Network model at the Central Luzon State University and penetrated the Network System using DOS/DDOS attack to simulate the real network scenario. This paper also presents the new approach Defense-through-Deception network security model that improves the traditional passive protection by applying deception techniques to them that give insights into the limitations posed by the Defense-In-Depth (DID) Model. Furthermore, this model is designed to prevent an attacker who has already entered the network from doing damage.

Este artigo apresenta uma reflexão sobre a relação entre futebol e criação/recriação de identidades. Ele tem por objetivo levantar aspectos sociais, culturais, políticos e individuais que tornam o futebol uma escolha que localiza o sujeito no grupo, posiciona-o socialmente e o investe de sentimentos e sentidos peculiares em torno da associação futebolística, da torcida e da paixão, revelando o porquê de se vestir a “camisa” do time. Futebol é mais do que mera diversão, e, ao pensá-lo como “válvula de escape”, coloca-se a questão do jogo de poder e das identidades presentes na produção e reprodução real e simbólica de seus elementos no cotidiano,ontem e hoje.

Security policies have different components; firewall, active directory, and IDS are some examples of these components. Enforcement of network security policies to low level security mechanisms faces some essential difficulties. Consistency, verification, and maintenance are the major ones of these difficulties. One approach to overcome these difficulties is to automate the process of translation of high level security policy into low level security mechanisms. This paper introduces a framework of an automation process that translates a high level security policy into low level security mechanisms. The framework is described in terms of three phases; in the first phase all network assets are categorized according to their roles in the network security and relations between them are identified to constitute the network security model. This proposed model extends the organization based access control (OrBAC) model to include not only access control policy but also some other administrative security policies like auditing policy. Besides, it enables matching of each rule of the high level security policy with the corresponding ones of the low level security policy. Through the second phase, the high level security policy is mapped into the network security model. The second phase could be considered as a translation of the high level security policy into an intermediate model level. Finally, the intermediate model level is translated automatically into low level security mechanism. The paper illustrates the applicability of proposed approach through an application example.

With the development and popularization of the Internet, network security has become the focus of public attention. Operating system detection and identification is an important part of network security work, which has very important significance for its research. This thesis designs an algorithm of operating system identification based on random forest. Based on the third-party fingerprint database, this method constructs simulation data and maps it into a vector that can be learned by the algorithm. In order to construct a highly reliable and generalized resource fingerprint structure, a random forest algorithm is used to combine multiple weak fingerprints into Strong fingerprints to improve the accuracy of operating system recognition, and design a layered training architecture to achieve long-term expansion and maintenance of operating system fingerprint models based on random forest construction. The fingerprint similarity algorithm is adopted to measure the similarity between fingerprints, which provides a basis for the operating system to mark the card. Experiments show that this method can accurately identify the remote operating system, and has a better accuracy effect than the traditional static matching method.

Network security assessment is a complex multi-criteria problem including both quantitative and qualitative factors. In this paper, taken the computer network security evaluation index for a research object, the judgment matrix of index weight was improved based on the fuzzy theory, and a new weight determination approach was proposed to make up the shortcomings of traditional weight determination method and highlight the fuzziness of expert judgment. Meanwhile using fuzzy theory to establish fuzzy evaluation matrix, then combine analytic hierarchy process to set up a fuzzy AHP evaluation model of the computer network security. At the final stage, a security assessment of the system of an institution’s network was to implement to demonstrate the feasibility of the evaluation model.

The modern world technology is civilized, globalized and modernized. The technological development of social networks and e-commerce applications produce larger data. This data communication is major task, because device to device communication need network terminal. This data transmission is not safe because of different types of tools and software available to destroy the existing network. In the field of network security during data transfer from one particular node to other node some security vulnerability is happened this is the one of the critical issue in this sector. The reason for this network security is different types of data attacks are happen in day to day life. It is easy to establish a new network but protecting the entire network is a big issue. This network security is generally two parameter first one is communication and second one is data automation. The network security field is directly or indirectly linked with the concept of data encryption. The development in this network security has taken us to a level that from signature again we came back to thumb print. For example maintain the data secure we use the lock system which is a finger print type. This technology helps us to protect the physical data theft, but logical data theft is still problem for data transmission. This article will brief about the network security it also presents the various network security types. Those types are wired and wireless network security. Apart from the network security the following topics is also discussed in this article. Those are network security protocols and simulation tools in network security. The research problems in network security are privacy and vulnerability of data.

ABSTRACTTraditional protection measures are difficult to cope with in complex and changeable network attacks. This paper presents an innovative construction of a hybrid model based on the combination of graph neural network (GNN) and random forest (RF), and uses an adaptive feature selection mechanism and multi‐task learning strategy to carry out network security big data prediction analysis. Through experiments on CICIDS 2017 and KDD Cup 1999 datasets, the results show that the model has excellent performance in detecting various types of attacks, with an accuracy of up to 0.94 in DoS attack detection of the CICIDS 2017 dataset, and maintains strong robustness in different noise environments. The model performs outstandingly in training efficiency, generalization ability, and multi‐task learning performance, and significantly improves the accuracy and efficiency of network security threat prediction. Research shows that this model has opened up a new path for network security protection, has important value in dealing with complex network attack scenarios, and provides strong support for the development of the network security field.

Cyber security threats to power systems are constantly evolving, and traditional security protection means are difficult to cope with new and complex attacks. This paper proposes a global situational awareness system for IT terminals based on artificial intelligence, which realizes real-time monitoring and early warning of IT terminals and networks through intelligent analysis and active defense. The system adopts a global data collection method to comprehensively monitor user operational behavior and network traffic through a user behavior data collection tool based on browser plug-ins and a network traffic collection tool based on agent software. To address the issues of user operational behavior deviation and network traffic security, the system introduces a user behavior analysis model based on graph matching algorithm and a network security situational awareness model, which can effectively identify abnormal user behavior and potential risks of the power grid, and significantly improve the system response capability. The system has been applied in the power grid industry and has shown excellent protection effects in the complex and changing network environment.

Network Security Situation Awareness (NSSA) can provide holistic status to administrator, and most related works rely on real time packet inspection technique to detect the security attacks which are happening and may already have caused some damage. In this paper, we propose the Risk Assessment NSSA model which collects the vulnerabilities information and uses corresponding risk level to qualitatively represent the security situation. This model is easy to apply and conveniently helps the administrator to monitor the whole network and be alerted to possible threat in future.