In the digital campus network security construction, the existence of potential security vulnerabilities can easily cause serious threats to campus information security, resulting in significant losses. In order to prevent and mitigate the risk, the article designs a security vulnerability identification system. Firstly, the URL similarity is compared by machine learning in order to scan the vulnerability information. The SeCF embedding layer is utilized to improve the input speed and the discard layer is designed to improve the overfitting problem during the training process. Finally, TextACBL security vulnerability identification model is proposed by combining CA, 1D-CNN and BiLSTM techniques and analyzed numerically. The average recognition rate of this paper’s method is as high as 80% for 10 common security vulnerabilities, which achieves better security vulnerability recognition results compared with existing methods such as cppcheck, deepbugs, flawfinder and vuldeepecker. The experimental results verify the effectiveness and feasibility of the method in this paper, which provides ideas for safeguarding campus network security during the construction of digital campus.