With the rapid development of Internet of Things (IoT) technology, the supervision and protection of computer network information security (NIS) has become particularly important. In view of backward technology problems, difficult management, and weak user security awareness in the supervision and protection of information security in traditional computer networks, this article discusses the corresponding supervision and protection strategies through the information technology (IT) of the IoT. In this paper, an effect model is established using horizontal regression and the differences between different classification levels are calculated. Regression loss is obtained through the loss function, a network intrusion detection model is established, and finally the encryption process and the output ciphertext are calculated to verify the feasibility of the model in practical applications. This paper is based on the comparative experiment of establishing traditional defense methods and NIS protection methods under the information technology of the IoT. The results show that the new security protection system under the IoT information technology has increased the perception of information security risks by 8%. The regulatory accuracy of the method studied in this paper is greater than 93. 77%, while that based on deep learning (DL) is below 92. 93%. This research not only helps to improve the protection ability of computer NIS in the IoT environment, but also provides a useful reference and reference for research and practice in related fields.

Lian Xue. Investigation of Computer Network Information Security Supervision and Protection Strategies based on Internet of Things. International Journal of Multimedia Computing (2025), Vol. 6, Issue 1: 1-18. https://doi.org/10.38007/IJMC.2025.060101.

[1] Chen J X. (2018). Analysis of computer network information security and protection under big data. Information Technology and Informatization, 68 (7): 1-15. 

[2] Zhao M, Wang X Z. (2018). Design and implementation of network information security system based on CA technology. Journal of Science of Teachers' College and University, 58 (13): 1-7. 

[3] Kansal L, Baqasah A M. (2022). Implementation of network information security monitoring system based on adaptive deep detection. Journal of Physics Conference Series, 31 (1): 454-465. 

[4] Deb R, Roy S. (2021). A Software Defined Network information security risk assessment based on Pythagorean fuzzy sets. Expert Systems with Applications, 183 (9): 1-17. 

[5] Yin C. (2021). Application of Virtual Private Network Technology in University Network Information Security. Journal of Physics Conference Series, 1915 (4): 42-71. 

[6] Wang Z, Zheng X. (2021). Application of internet of things information security in the informationization of sports training and education. Journal of Intelligent and Fuzzy Systems, 9 (4): 1-7. 

[7] Yao Y, Tong X. (2019). Dynamically Reconfigurable Encryption and Decryption System Design for the Internet of Things Information Security. Sensors, 19 (1): 143-160. 

[8] Li M, Botchey F E. (2021). Human factor, a critical weak point in the information security of an organization's Internet of things. Heliyon, 7 (3): 65-72. 

[9] Yhl A, Shuang Z. (2020). Information security and storage of Internet of Things based on block chains. Future Generation Computer Systems, 10 (6): 296-303. 

[10] Liang N. (2020). Security Transmission and Storage of Internet of Things Information Based on Blockchain. IOP Conference Series: Materials Science and Engineering, 750 (1): 159-164. 

[11] Geng Q, Tang X, Wang L. (2019). Discussing the Influencing Factors of Information Security from the Perspective of Organizational Management. Chinese Journal of Health Informatics and Management, 19 (2): 116-137. 

[12] Wang X, Lei W, Jia R. (2018). An Empirical Study on the Influencing Factors of the Security Behavior in Personal Information in Social Networks. Library and Information Service, 40 (2): 34-47. 

[13] Fang S H, Peng X Y. (2029). IoT information record based on blockchain technology secure storage. Natural Science Edition, 30 (1): 117-138. 

[14] Gao Y, Hasegawa H, Yamaguchi Y. (2022). Malware Detection Using Gradient Boosting Decision Trees with Customized Log Loss Function. Aerospace science and technology, 121 (2): 45-50. 

[15] Farhan A K, Ali R S. (2017). Secure location map and encryption key based on intelligence search algorithm in encryption and steganography to data protection. 2019. Acta Physica Sinica, 66 (23): 690-698.