Research on Spurious-Negative Sample Augmentation-Based Quality Evaluation Method for Cybersecurity Knowledge Graph
As the forms of cyber threats become increasingly severe, cybersecurity knowledge graphs (KGs) have become essential tools for understanding and mitigating these threats. However, the quality of the KG is critical to its effectiveness in cybersecurity applications. In this paper, we propose a spurio...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/13/1/68 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841549176205213696 |
|---|---|
| author | Bin Chen Hongyi Li Ze Shi |
| author_facet | Bin Chen Hongyi Li Ze Shi |
| author_sort | Bin Chen |
| collection | DOAJ |
| description | As the forms of cyber threats become increasingly severe, cybersecurity knowledge graphs (KGs) have become essential tools for understanding and mitigating these threats. However, the quality of the KG is critical to its effectiveness in cybersecurity applications. In this paper, we propose a spurious-negative sample augmentation-based quality evaluation method for cybersecurity KGs (SNAQE) that includes two key modules: the multi-scale spurious-negative triple detection module and the adaptive mixup based on the attention mechanism module. The multi-scale spurious-negative triple detection module classifies the sampled negative triples into spurious-negative and true-negative triples. Subsequently, the attention mechanism-based adaptive mixup module selects appropriate mixup targets for each spurious-negative triple, constructing partially correct triples and achieving more precise sample generation in the entity embedding space to assist in training the KG quality evaluation models. Through extensive experimental validation, the SNAQE model not only performs excellently in general-domain KG quality evaluation but also achieves outstanding outcomes in the cybersecurity KGs, significantly enhancing the accuracy and F1 score of the model, with the best F1 score of 0.969 achieved on the FB15K dataset. |
| format | Article |
| id | doaj-art-c58cea352a524fee8920205adea21bad |
| institution | Kabale University |
| issn | 2227-7390 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj-art-c58cea352a524fee8920205adea21bad2025-01-10T13:18:09ZengMDPI AGMathematics2227-73902024-12-011316810.3390/math13010068Research on Spurious-Negative Sample Augmentation-Based Quality Evaluation Method for Cybersecurity Knowledge GraphBin Chen0Hongyi Li1Ze Shi2School of Cyber Science and Technology, Beihang University, Beijing 100191, ChinaSchool of Cyber Science and Technology, Beihang University, Beijing 100191, ChinaSchool of Cyber Science and Technology, Beihang University, Beijing 100191, ChinaAs the forms of cyber threats become increasingly severe, cybersecurity knowledge graphs (KGs) have become essential tools for understanding and mitigating these threats. However, the quality of the KG is critical to its effectiveness in cybersecurity applications. In this paper, we propose a spurious-negative sample augmentation-based quality evaluation method for cybersecurity KGs (SNAQE) that includes two key modules: the multi-scale spurious-negative triple detection module and the adaptive mixup based on the attention mechanism module. The multi-scale spurious-negative triple detection module classifies the sampled negative triples into spurious-negative and true-negative triples. Subsequently, the attention mechanism-based adaptive mixup module selects appropriate mixup targets for each spurious-negative triple, constructing partially correct triples and achieving more precise sample generation in the entity embedding space to assist in training the KG quality evaluation models. Through extensive experimental validation, the SNAQE model not only performs excellently in general-domain KG quality evaluation but also achieves outstanding outcomes in the cybersecurity KGs, significantly enhancing the accuracy and F1 score of the model, with the best F1 score of 0.969 achieved on the FB15K dataset.https://www.mdpi.com/2227-7390/13/1/68cybersecurityquality evaluationspurious-negative tripleknowledge graphs |
| spellingShingle | Bin Chen Hongyi Li Ze Shi Research on Spurious-Negative Sample Augmentation-Based Quality Evaluation Method for Cybersecurity Knowledge Graph Mathematics cybersecurity quality evaluation spurious-negative triple knowledge graphs |
| title | Research on Spurious-Negative Sample Augmentation-Based Quality Evaluation Method for Cybersecurity Knowledge Graph |
| title_full | Research on Spurious-Negative Sample Augmentation-Based Quality Evaluation Method for Cybersecurity Knowledge Graph |
| title_fullStr | Research on Spurious-Negative Sample Augmentation-Based Quality Evaluation Method for Cybersecurity Knowledge Graph |
| title_full_unstemmed | Research on Spurious-Negative Sample Augmentation-Based Quality Evaluation Method for Cybersecurity Knowledge Graph |
| title_short | Research on Spurious-Negative Sample Augmentation-Based Quality Evaluation Method for Cybersecurity Knowledge Graph |
| title_sort | research on spurious negative sample augmentation based quality evaluation method for cybersecurity knowledge graph |
| topic | cybersecurity quality evaluation spurious-negative triple knowledge graphs |
| url | https://www.mdpi.com/2227-7390/13/1/68 |
| work_keys_str_mv | AT binchen researchonspuriousnegativesampleaugmentationbasedqualityevaluationmethodforcybersecurityknowledgegraph AT hongyili researchonspuriousnegativesampleaugmentationbasedqualityevaluationmethodforcybersecurityknowledgegraph AT zeshi researchonspuriousnegativesampleaugmentationbasedqualityevaluationmethodforcybersecurityknowledgegraph |