Abstract

Encryption is widely used to ensure the security and confidentiality of information. Because people trust in encryption technology, a series of attack methods based on certificates have been derived. Malicious certificates protect many malicious behaviors and threaten data security. To counter this threat, machine learning algorithms are widely used in malicious certificate detection. However, the detection efficiency of such algorithms largely depends on whether the extracted features can effectively represent the data. In contrast, graph convolutional networks (GCNs) can automatically extract useful features. GCNs are powerful at fitting graph data, which can improve the effectiveness of learning systems by efficiently embedding prior knowledge in an end-to-end manner. In this paper, we propose an algorithm for detecting malicious digital certificates with GCNs. Firstly, we transform the digital certificate dataset with pem document structure into a corpus of graph structure based on attribute co-occurrence and document attribute relations. Then, we put the graph structure certificate dataset into a GCN for training. The results of the experiment show that GCN is very effective in certificate classification and outperforms traditional machine learning algorithms and extant neural network algorithms. The accuracy of our algorithm to detect malicious certificates is 97.41%. This shows that our algorithm is very effective.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.