Lin Shi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Lin Shi has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
Liquan Chen
Southeast University, School of Cyber Science and Engineering, Nanjing, China
3 shared publicationsJie Chen
Jiangsu Financial Information Management Center, Nanjing, China
2 shared publicationsNing Chen
Jiangsu Water Conservancy Network Data Center, Nanjing, China
2 shared publicationsRui Zhu
School of Cyber Science and Engineering, Southeast University, Nanjing, China
2 shared publications- Shah Nazir
Department of Computer Science University of Swabi Swabi Pakistan
2 shared publications Zilong Wang
Nanjing University of Aeronautics and Astronautics, College of Economics and Management, Nanjing, China
2 shared publications
Latest Publications
- Open Access
- 26 September 2022
- Published by Wiley in Computational Intelligence and Neuroscience
- Vol. 2022, 1-10
The Application of Computer Intelligence in the Cyber-Physical Business System Integration in Network Security
In order to address the false alarm detection problem caused by the inability to identify the transgression scene pages in the process of horizontal transgression detection, this study proposes a deep learning-based LSTM-AutoEncoder unsupervised prediction model. The model uses long short-term memory network to build AutoEncoder, extracts text features of page response data of horizontal transgression scenario, and reconstructs text features to restore. Meanwhile, it counts the error between the restored result and the original page response, judges whether the detection result of horizontal transgression is false alarm according to the error threshold of unknown page, and tests the effectiveness of the model effect under real business data by comparing it with other two algorithms, one-class SVM and AutoEncoder, which provides security for enterprise network business. The results show that the LSTM-AutoEncoder model achieves a more balanced index in terms of accuracy, precision, recall, and F1-score in the case of MAE, which is 0.3 more and 0.2 more than the case of MSE in terms of recall and accuracy. It is concluded that the LSTM-AutoEncoder model is more in line with the real business requirements, and the simple model architecture selected for this study can reduce the complexity of the model, speed up the prediction time of the model in the application phase, and improve the performance of the detection software. This indicates that this study has some application prospects in network security.
- 26 September 2022
- Published by Wiley in Computational Intelligence and Neuroscience
- Vol. 2022, 1-10
Open AccessThe Application of Computer Intelligence in the Cyber-Physical Business System Integration in Network Security
In order to address the false alarm detection problem caused by the inability to identify the transgression scene pages in the process of horizontal transgression detection, this study proposes a deep learning-based LSTM-AutoEncoder unsupervised prediction model. The model uses long short-term memory network to build AutoEncoder, extracts text features of page response data of horizontal transgression scenario, and reconstructs text features to restore. Meanwhile, it counts the error between the restored result and the original page response, judges whether the detection result of horizontal transgression is false alarm according to the error threshold of unknown page, and tests the effectiveness of the model effect under real business data by comparing it with other two algorithms, one-class SVM and AutoEncoder, which provides security for enterprise network business. The results show that the LSTM-AutoEncoder model achieves a more balanced index in terms of accuracy, precision, recall, and F1-score in the case of MAE, which is 0.3 more and 0.2 more than the case of MSE in terms of recall and accuracy. It is concluded that the LSTM-AutoEncoder model is more in line with the real business requirements, and the simple model architecture selected for this study can reduce the complexity of the model, speed up the prediction time of the model in the application phase, and improve the performance of the detection software. This indicates that this study has some application prospects in network security.
- 15 September 2022
- Published by SPIE-Intl Soc Optical Eng in Journal of Electronic Imaging
- Vol. 32 (01) , 011214-12
(Retracted) Research on computer network security evaluation based on image recognition and neural network
In today’s social development, the level of informatization has been greatly improved. Computer networks are now used in all aspects of society, especially with the popularity of mobile phones and computers. Basically, a mobile phone is a computer that stores all the information of a person, so it is indispensable for carrying out research on computer network security evaluation. The purpose of this article is to examine the growing state of information security threats in computer networks. Neural network technology, which is considered secure, has high flexibility, fast access to information, strong logic, and low failure. Toward creating a low-cost network topology, we used a low-cost network risk assessment method to assess the security of computer networks based on neural networks, and we evaluated existing risks that are appropriate for future computer security research. The results of the study show that neural networks using the Bayesian network method have a significant impact on network security. Considering the problems that can occur with information security risks, computer security systems based on neural networks have a 30% reduction in information error rate compared with traditional methods, and computer network systems based on neural networks have better learning performance to safeguard network security. Improving the security of information requires further research and evaluation of computer network security based on neural networks.
- 15 September 2022
- Published by SPIE-Intl Soc Optical Eng in Journal of Electronic Imaging
- Vol. 32 (01) , 011214-12
(Retracted) Research on computer network security evaluation based on image recognition and neural network
In today’s social development, the level of informatization has been greatly improved. Computer networks are now used in all aspects of society, especially with the popularity of mobile phones and computers. Basically, a mobile phone is a computer that stores all the information of a person, so it is indispensable for carrying out research on computer network security evaluation. The purpose of this article is to examine the growing state of information security threats in computer networks. Neural network technology, which is considered secure, has high flexibility, fast access to information, strong logic, and low failure. Toward creating a low-cost network topology, we used a low-cost network risk assessment method to assess the security of computer networks based on neural networks, and we evaluated existing risks that are appropriate for future computer security research. The results of the study show that neural networks using the Bayesian network method have a significant impact on network security. Considering the problems that can occur with information security risks, computer security systems based on neural networks have a 30% reduction in information error rate compared with traditional methods, and computer network systems based on neural networks have better learning performance to safeguard network security. Improving the security of information requires further research and evaluation of computer network security based on neural networks.
- 25 July 2022
- Published by SPIE-Intl Soc Optical Eng in Journal of Electronic Imaging
- Vol. 32 (01) , 011207-14
(Retracted) Software development and design of network security system based on log data
With the rapid development of computer network technology and the fact that the network brings convenience to people’s lives and work, security issues cannot be ignored. Various countries and social organizations build a network security vulnerability database based on big data analysis technology, use network offensive and defensive platforms to train network security talents, and the target environment as a core component in the offensive and defensive platforms plays an important role in practice. We construct a large network security data set with a security knowledge system, analyze the current construction technology and vulnerability data characteristics of major vulnerability databases at home and abroad from multiple levels, and propose a vulnerability information correlation technology based on a combination of general vulnerability numbers and specific vulnerability numbers. Also, we comprehensively analyze each vulnerability database, assess the comprehensiveness and coverage of the vulnerability data information covered, and establish the source of the vulnerability data, data reference, security content automation protocol support, proof of concept, platform environment affected by the vulnerability exploitation code situation, and other fields of network security big data sets with security knowledge system. Here, we have completed the design and implementation of the user rights management module, the centralized monitoring module, and the service desk and configuration change management module. The system can accurately monitor the operation of the system in real time, find problems in time, warn of potential risks, and promote the operation and maintenance approach to intelligent. The transformation has improved the efficiency of fault diagnosis and greatly enhanced the safety of the system. Experimental research shows that the software system automatically screens and manually confirms the vulnerabilities that meet the target construction environment, and initially constructs a total of 43 effective target environments, which provides security researchers with the understanding of vulnerability principles, hazards, and targeted network security training. A stable and convenient experimental environment.
- 25 July 2022
- Published by SPIE-Intl Soc Optical Eng in Journal of Electronic Imaging
- Vol. 32 (01) , 011207-14
(Retracted) Software development and design of network security system based on log data
With the rapid development of computer network technology and the fact that the network brings convenience to people’s lives and work, security issues cannot be ignored. Various countries and social organizations build a network security vulnerability database based on big data analysis technology, use network offensive and defensive platforms to train network security talents, and the target environment as a core component in the offensive and defensive platforms plays an important role in practice. We construct a large network security data set with a security knowledge system, analyze the current construction technology and vulnerability data characteristics of major vulnerability databases at home and abroad from multiple levels, and propose a vulnerability information correlation technology based on a combination of general vulnerability numbers and specific vulnerability numbers. Also, we comprehensively analyze each vulnerability database, assess the comprehensiveness and coverage of the vulnerability data information covered, and establish the source of the vulnerability data, data reference, security content automation protocol support, proof of concept, platform environment affected by the vulnerability exploitation code situation, and other fields of network security big data sets with security knowledge system. Here, we have completed the design and implementation of the user rights management module, the centralized monitoring module, and the service desk and configuration change management module. The system can accurately monitor the operation of the system in real time, find problems in time, warn of potential risks, and promote the operation and maintenance approach to intelligent. The transformation has improved the efficiency of fault diagnosis and greatly enhanced the safety of the system. Experimental research shows that the software system automatically screens and manually confirms the vulnerabilities that meet the target construction environment, and initially constructs a total of 43 effective target environments, which provides security researchers with the understanding of vulnerability principles, hazards, and targeted network security training. A stable and convenient experimental environment.
- 10 May 2021
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 80 (20) , 31465
Correction to: Secure convergence of artificial intelligence and internet of things for cryptographic cipher-a decision support system
- 10 May 2021
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 80 (20) , 31465
Correction to: Secure convergence of artificial intelligence and internet of things for cryptographic cipher-a decision support system
- 14 February 2021
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 80 (20) , 31451-31463
Secure convergence of artificial intelligence and internet of things for cryptographic cipher- a decision support system
- 14 February 2021
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 80 (20) , 31451-31463
Secure convergence of artificial intelligence and internet of things for cryptographic cipher- a decision support system
- Open Access
- 18 December 2019
- Published by Springer Nature in Research Square
Data Service Trust Measurement in Cloud Environment
Highly trusted issues will be one of the main obstacles to a new era of highly trusted cloud computing. In the cloud computing environment, because sensitive applications and user data are put into the cloud, they run in virtual machines in the data center. Among them, due to the existence of access vulnerability, virtualization vulnerability, web application vulnerability, etc., high trust issues arise from data control, identity authentication, lack of information and other related issues. The introduction of trust mechanisms can be very facilitate the solution of related issues, achieve highly trusted quantification, analysis, and modeling of cloud data centers, meet high trust requirements, and provide users with a highly trusted cloud computing environment. This article mainly studies the trust measure of data services in cloud environment. In this paper, the optimization scheme is verified through experiments, and the traditional big data processing scheme, the original Sahara and the optimization scheme are compared in six cases. Overall, the optimization scheme has a significant performance improvement. Compared with the default configuration of Sahara, the configuration of the new interface has increased the throughput in DFSIO by 120%. Using the design of the unified cache management service, Tachyon can reach 13 in specific situations. In the execution time of Sort workloads, the optimization scheme generally decreased by about 50% compared to the original Sahara, and the memory utilization increased from 80% to 96% in our experiments, but in the cache isolation and other areas need to be improved. The results are basically in line with expectations, which also confirms the rational thinking and value of this article on BDAaS performance research.
- 18 December 2019
- Published by Springer Nature in Research Square
Open AccessData Service Trust Measurement in Cloud Environment
Highly trusted issues will be one of the main obstacles to a new era of highly trusted cloud computing. In the cloud computing environment, because sensitive applications and user data are put into the cloud, they run in virtual machines in the data center. Among them, due to the existence of access vulnerability, virtualization vulnerability, web application vulnerability, etc., high trust issues arise from data control, identity authentication, lack of information and other related issues. The introduction of trust mechanisms can be very facilitate the solution of related issues, achieve highly trusted quantification, analysis, and modeling of cloud data centers, meet high trust requirements, and provide users with a highly trusted cloud computing environment. This article mainly studies the trust measure of data services in cloud environment. In this paper, the optimization scheme is verified through experiments, and the traditional big data processing scheme, the original Sahara and the optimization scheme are compared in six cases. Overall, the optimization scheme has a significant performance improvement. Compared with the default configuration of Sahara, the configuration of the new interface has increased the throughput in DFSIO by 120%. Using the design of the unified cache management service, Tachyon can reach 13 in specific situations. In the execution time of Sort workloads, the optimization scheme generally decreased by about 50% compared to the original Sahara, and the memory utilization increased from 80% to 96% in our experiments, but in the cache isolation and other areas need to be improved. The results are basically in line with expectations, which also confirms the rational thinking and value of this article on BDAaS performance research.