Journal of Cyber Security and Mobility

Identification of SQL Injection Security Vulnerabilities in Web applications Based on Binary Code Similarity

2024-06-06T08:33:24+02:00

The existing SQL injection security vulnerability identification technology for Web applications has inherent flaws, which are relatively passive in defense methods, and cannot deal with increasingly changeable attack methods. In order to improve the accuracy of SQL injection security vulnerability identification of Web applications, this paper uses an improved skip-gram model to realize unsupervised learning of the embedding process, converts the information related to program functions contained in the vertices of the basic block into feature vectors to obtain the ACFG vector of the basic block, and measures the similarity of binary functions by evaluating the similarity of feature vectors. The experimental results show that the technical processing route proposed in this paper can effectively compare binary functions with different architectures and optimization levels, and use the advantages of neural networks to obtain higher accuracy and better analysis efficiency, thereby effectively improving the identification effect of SQL injection security vulnerabilities in Web applications. Therefore, it can play a certain role in the security management of subsequent Web applications.

Research on Security Situation Assessment and Prediction Model of Network System in Deep Learning Environment

2024-07-11T04:19:46+02:00

With the development of the Internet, the network environment is increasingly complex, and the problem of network security is increasingly serious. Traditional passive network security technology has been unable to meet people’s current security needs, in this context, network security situation awareness arises at the historic moment. NSSA technology makes the traditional passive security into active security, from the analysis of unilateral elements to the analysis of the overall security. As key technology of situation perception, security situation assessment and prediction can evaluate and predict the network security situation at the overall level, help network security managers understand the overall network security changes and take protective measures in advance when predicting the dangerous state, which has important research significance. This paper mainly studies the situation assessment and prediction technology of network security, and puts forward the improved model and algorithm, which improves accuracy of situation assessment and prediction results. Prediction accuracy reaches 97.86%, and the efficiency of the situation assessment reaches 98.22%.

Research on the Quality Assessment and Protection of Network Security Body Based on Intelligent Induction and Deep Learning

2024-07-11T03:41:58+02:00

This mechanism mainly saves the induction information in the distributed cloud storage node, and saves the message summary of the induction information in the block chain node, and then the corresponding relationship between the cloud storage node and the block chain node is saved in the induction information management machine. When the user reads the data, the identity authentication is first completed at the induction information management machine, and the induction information is obtained through the key, and finally the data verification is completed at the block chain node. The main advantages of this mechanism are: using block chain to store intelligent sensing information, and using chain storage to reduce the cost of storage, thus enhancing the scalability of block chain storage. This mechanism uses new hash chains to transmit inductive information, thus improving the security of transmission. Through this study proposes an access control strategy for intelligent sensing information. In this way, the user with the key can quickly complete the work certificate and complete the access, while the illegal intruder who does not hold the key cannot calculate the work certificate of the next block based on the existing block, so he cannot access the intelligence. Under the network topology set in this paper, the model with step 2 is significantly better than step 1 and 3, with 18.30% and 75.01% reduction on MAPE and 15.66% and 87.79% reduction on RMSE. Through hidden Markov, the security situation of the information system under the time series is determined. Through SSIPN, the security event is not used as a single situation assessment index, but the network topology and node vulnerability are included in the assessment scope to enhance the correlation between the security event and each node in the information system. Based on SSIPN, the weight allocation algorithm of the corresponding nodes is proposed, which accurately reflects the impact of the level of the nodes on the network on the overall situation, and realizes the security situation assessment of the overall network.

Study on Traffic Anomaly Detection of Wireless Communication Network Based on Fuzzy Relation Equation

2024-06-27T09:07:59+02:00

As the core technology of intrusion detection system, network abnormal traffic detection has always been an important research direction in academia and industry. Related studies show that the failure to find the abnormal situation in the network in time will cause incalculable damage to the computer system and even the whole network. With the emergence of large-scale lightweight terminal nodes, whose characteristics of low computing power and continuous data collection, a distributed abnormal traffic detection technology has emerged. As a kind of distributed structure with decentralized data, federated learning can not only protect local data privacy, reduce communication overhead, but also achieve the effect of centralized training, However, in the era of the Internet of Things with heterogeneous network integration and regular access of massive terminals, the network traffic distribution of different devices is differentiated due to the different security needs of diversified terminals. This will lead to the traditional federated learning-based network anomaly traffic detection facing two major challenges, the uneven data distribution leads to the model training cannot be optimized, and the distributed training global model is not suitable for local network anomaly traffic detection. The scheme of this paper showed significant advantages in the performance evaluation of backbone and mission UAVs, achieving an accuracy of 92.47% and 93.01%, respectively. In contrast, the accuracy of the traditional federated learning method is 89.87% and 89.11%, respectively, which is slightly lower than the present scheme. We propose a framework and algorithm for network anomalous traffic detection based on cluster federated learning. Taking the Internet of Vehicles as the background, the security requirements of the devices connected to the Internet of Vehicles are analyzed, and a set of federated learning data sets meeting the distribution of network traffic in practical applications are constructed with the field recognized data set KDDCup99. This paper verifies the excellent performance of the network anomaly traffic detection mechanism based on cluster federated learning in the case of heterogeneous data distribution.

Research on Fast Early Warning of False Data Injection Attack in CPS of Electric Power Communication Network

2024-07-25T01:22:22+02:00

The power grid is vulnerable to bad data interference and false data attacks, so its security is reduced. This paper focuses on the study of false data injection attacks (FDIAs), analyzes the principle of FDIAs and their impact on power systems, and studies the methods of suppressing and detecting FDIAs based on distributed state estimation and neural networks. In addition, this paper establishes a specific simulation model. Simulation results show that the proposed method can effectively identify FDIAs and correct bad data, thus further reducing the impact of FDIAs on power system state estimation. Therefore, in the follow-up, we can use this method to carry out practical research in the power communication network to further improve the security of the power communication network.

Optimization of Network Intrusion Detection Model Based on Big Data Analysis

2024-07-31T21:56:11+02:00

As user usage grows, so do security threats to networks, the Internet, websites, and organizations. Detecting intrusions in such a big data situation is complex. A feature-optimized network intrusion detection model based on extensive data analysis is designed to overcome the limitations of current network intrusion detection models and obtain more ideal results. Firstly, the current modeling status of network intrusion detection is studied, and the influence of features on the results of network intrusion detection is analyzed. Then, the feature optimization mathematical model of network intrusion detection is established. The solution of the feature optimization mathematical model is searched by an adaptive genetic algorithm simulating natural biological evolution. The optimal feature subset of intrusion detection is obtained by back coding the optimal solution. Finally, according to the optimal feature subset, the learning sample of network intrusion detection is modeled, and the optimal network intrusion detection model is designed. Using the standard data set of network intrusion detection for simulation and comparison tests, the average accuracy of this paper’s network intrusion detection model is about 95%, while other current network intrusion detection models are below 95%. Meanwhile, the time of training and the detection of intrusion detection modeling in this model is significantly reduced, and better efficiency of network intrusion detection can be obtained.

Research on Optimization of UAV Communication Network Security Protection Strategy Based on Advanced Encryption Technology

2024-07-25T01:23:59+02:00

With the wide application of UAVs in various applications, the security, spectrum, and energy efficiency of their communication networks have become increasingly prominent. This paper proposes a joint optimization strategy based on deep reinforcement learning for drone swarm communication networks. First, a model is constructed that takes into account security threats, spectrum sharing, and energy consumption. Intelligent agents are then trained through deep reinforcement learning to dynamically select the best spectrum allocation and energy strategy to improve spectrum and energy efficiency while maintaining network security. Based on encryption technology, this paper studies resource optimization strategies for UAV security communication in different scenarios. Aiming at the incomplete certainty of multiple eavesdropping positions and the problem of the no-fly zone during UAV flight, a joint optimization algorithm is proposed to optimize UAV trajectory, interference power, and transmission power of ground base stations so as to maximize the minimum average security capacity of the system in the worst case. To solve the problem of the LoS link of UAV being quickly blocked in the city and secondary users easily causing excessive interference to primary users, intelligent reflectors are introduced to assist the UAV in secure communication. IRS can be used to reconfigure channel parameters to control the propagation direction of UAV communication links, enhance the channel quality of the primary link, and weaken the channel quality of eavesdropping links and interference links. Simulation results show that the optimization scheme improves the channel quality of UAV in crowded scenarios, inhibits the eavesdropping effect of eavesdroppers on secondary security users, and reduces the spectrum multiplexing interference of primary users, thus significantly enhancing the security capacity of the system. When the interference power of UAVs is increased, the value and growth rate of the security capacity of security users are significantly increased. The increase is 20%. Through a large number of simulation experiments, it has been proved that this method has excellent performance in improving communication security, spectrum utilization, and energy efficiency and has obvious advantages over the traditional baseline and average allocation DQN-wrap method.

The Application of National Security Algorithm in Wireless Networks for Industrial Automation Process Automation (WIA-PA) Network Data Security Transmission

2024-09-29T23:13:33+02:00

Industrial wireless communication technology is the key to promoting the development of factory intelligence and automation. However, wireless network data security has hindered the development of industrial intelligence. Therefore, to solve the security issues of industrial wireless networks, a network data secure transmission technology based on the national security algorithm is proposed based on industrial wireless network standard protocols. Firstly, to address the vulnerability of network node identity authentication to attacks, the national security algorithm is used to construct a node authentication model. Secondly, a data security transmission model is constructed based on the improved national security algorithm, which can securely transmit industrial wireless networks by encrypting network application layer data. In network node identity authentication, when the step size was 50, the identity authentication average accuracy of the research mode reached over 98.95%, which was better than other models. When the step size was 50, the average accuracy of identity authentication in the research model was over 98.95%, showing the best performance among similar models. In the attack test of illegal client C, when the interaction history data was within 500, the node identity authentication was higher than 99.56%. However, when the interaction history data exceeded 500, the overall performance of the research model was still the best. In the comparison of node code storage and content usage overhead, when the code quantity was 15000, the storage overhead of the research model was 87356 bytes, with more node code storage and lower memory usage. The overall performance of the research model is better. From this, the research method performs the best in both identity recognition accuracy and security in network data security. The research content will provide technical support for the security management and data transmission of industrial wireless technology.

Design and Performance of Privacy Protection Model for Big Data Transmission Based on Mixed Encryption

2024-10-10T11:57:35+02:00

With the advent of the big data era, data security and privacy protection have become particularly important. Big data has advantages such as large scale and diverse types, but it also brings risks of personal privacy leakage and data abuse. However, the symmetric or asymmetric encryption techniques alone have limitations in big data security and privacy protection. Therefore, a privacy protection model for big data transmission based on mixed encryption is proposed and experimentally validated. The research results indicated that the asymmetric encryption algorithm used had an encryption time of less than 20 ms, and the key space occupation was only 0.031 Kb to 0.063 Kb. After improving the symmetric encryption algorithm, it achieved a lower correlation of 0.16 within 18 ms and increased the number of ciphertext transformations to an average of 82 bits. In the performance verification of mixed encryption technology for 60 MB data packets, the proposed mixed encryption technology took 273.1 ms, the decryption took 254.7 ms, the correlation was as low as 0.12, and the average resistance time in resisting violent attacks exceeded 100 s. The model proposed in the study improves the encryption and decryption speed while ensuring data security, which has important practical application value and theoretical significance for data privacy protection in big data environments.

Addressing The Concern of Malicious Drone in The Internet of Drone Sixth Generation Mobile System Powered by WSNs Using Three Security Levels

2024-09-19T19:53:31+02:00

Securing communications in drone networks is an essential aspect of ensuring good network performance. Data transferred over the Internet of Drones (IoD) Communications, which is rapidly growing, holds crucial information for navigation, coordination, data sharing, and control, and enables the creation of smart services in many sectors. Sixth-generation (6G) mobile systems are anticipated to be impacted by the plethora of IoD. The possibility of malevolent drones intercepting or altering data before it reaches its target is a serious worry. Operations on IoD networks may be hampered by this, and safety issues may arise. Utilizing three security levels, the suggested method solves the issue of malicious drones in the IoD network. The suggested system’s first level allocates a trust value to IoD drones based on behaviors including prior drone behavioral histories, packet losses, and processing delays. This can be accomplished by choosing drones as investigators to monitor the actions of neighboring drones and assess the level of trust value. The second level involves communication protection, which is accomplished by historical communication behavior. The purpose of the final security level is to safeguard the reliability of the data used to calculate trust values. The fundamental topical of our proposed system is to propose and explore a novel tactic for detecting malicious UAVs within the internet of drone framework, using theoretical and simulations models. Because that 6G networks are still now in the developmental stage, the results presented are based on predictive analyses and simulations rather than real-world applications.

K-means Optimized Network Security Management in the Internet Context

2024-06-21T10:56:03+02:00

The rapid development of the Internet has had a broad and profound impact on humanity, making information acquisition and dissemination more convenient. It has also brought significant opportunities and benefits to business and the economy. However, there are some issues, such as personal factors and data security concerns. In order to solve the above problems, the K-means algorithm is optimized from the perspectives of K-value validity index, feature weighting and three-branch decision making. First, the optimal clustering results are determined according to K-value validity index, and the influence of different dimensional features on clustering is considered for feature weighting, and the uncertain objects in the three-branch decision deadlock class are divided into the boundary domain. The delay decision of the boundary domain data is carried out, and the K-means clustering optimization algorithm is improved by combining the above three aspects, and the intelligent network security management system is developed on this basis. The results showed that the K-means optimization algorithm achieved the highest average accuracy rate, adjusted Morandi index, and adjusted mutual information across various datasets, with values of 96.01%, 0.866, and 0.869, respectively. In practical network attack scenarios, the K-means optimization algorithm attained an attack threat recognition accuracy of 94.38%. Under unknown network attack types, its detection rate and false alarm rate were 94.63% and 1.32%, respectively. Surveys conducted post-implementation of the intelligent network security management system indicated that over 90% of users were satisfied with their experience of the system. In summary, the proposed method accurately identifies potential network threats in network data, fulfilling performance requirements for network security management systems and ensuring the security of network resources.