2025 Vol.8 Aug.N04

• Title: Potential overflow vulnerability detection method for remote teaching and tutoring software based on artificial intelligence
• Name: Yuntao Lai, Haolin Wei , Baohua Ning , Jiajian Chen, Xiaomei Ya
• Company: GuangXi Vocational Normal University, Nanning, 530000 China
• Abstract:

   With the popularization of educational software, the security risks it faces are becoming increasingly prominent, especially the overflow defects, which seriously affect the stability of the system and the security of data. A method is proposed to detect potential overflow defects in remote education tutoring software using artificial intelligence technology to address this issue. Firstly, extract the characteristics of remote teaching tutoring software and abstract it into a multi-attribute mapping containing boundary labels. Then, using artificial intelligence technology, establish a vulnerability mining model to audit the code and detect defects and security risks in the code. Finally, by detecting potential leakage defects in the software source code, automatic localization of suspicious code can be achieved. Experimental results have shown that compared with the methods in references 1 and 2, the AI based remote teaching and tutoring software potential overflow vulnerability detection method can better detect potential overflow defects in the network. On the test set, the proposed method can correctly identify most known or unknown vulnerabilities.

  
  

• Keyword: Potential overflow vulnerabilities; Remote teaching; Vulnerability detection; Tutoring software; Artificial intelligence technology
• DOI: 10.12250/jpciams2025090811
• Citation form: Yuntao Lai, Haolin Wei , Baohua Ning ,Jiajian Chen,Xiaomei Yang.Potential overflow vulnerability detection method for remote teaching and tutoring software based on artificial intelligence[J]. Computer Informatization and Mechanical System,2025,Vol.8,pp.

[1] LI Z J, LI T, CHEN H D, et al. Software vulnerability detection method based on abstract syntax tree feature migration(AST-FMVD) [J]. Computer Technology and Development. 2024, 34(6), 81-88.

[2] FENG Q W, WANG D H, ZHANG D X. Simulation of software potential overflow vulnerability detection under LSTM-SVM algorithm [J]. Computer Simulation. 2024, 41(2), 487-491.

[3] ZHAO H P, XUE D Q, SHANG Z L. Simulation of software source code vulnerability detection based on human-computer interaction big data [J].  Computer Simulation. 2023, 40(11), 388-392+465.

[4] CHEN H D, LI L, QIAO M Q, et al. Software vulnerability detection based on mixed representation and cooperative training [J]. Computer Technology and Development. 2024, 34(5), 126-132.

[5] LIU J H, WAN M, ZHOU C X, et al. Vulnerability detection in java open source software based on bidirection LSTM [J]. Computer Applications and Software.  2020, 37(12), 322-327.

[6] FAN C, QU Z G, WANG B W, et al. CS-GNN:A class-sensitive graph neural network for real-world vulnerability detection [J]. Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition). 2024, 36(5), 1042-1051.

[7] WANG Y, FAN L, ZHAO N N. Sequential recommendation model using gated network to construct user’s dynamic interest [J]. Computer Engineering. 2022, 48 (8), 283-291.

[8] LUO R R, GONG H F, XU D. Multilayer gating and relational graph attention fusion network for aspect-based sentiment analysis [J]. Computer Engineering and Applications. 2023, 59(15), 169-176. 

[9] TONG W G, ZENG S C, ZHANG L F. Multi-scale convolutional neural network algorithm for electrical resistance tomography [J]. Computer Applications and Software. 2024, 41(5), 177-182.