Domain-constrained Synthesis of Inconsistent Key Aspects in Textual Vulnerability Descriptions
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908666661175296 |
|---|---|
| author | Han, Linyi Pan, Shidong Xing, Zhenchang Yitagesu, Sofonias Zhang, Xiaowang Feng, Zhiyong Sun, Jiamou Huang, Qing |
| author_facet | Han, Linyi Pan, Shidong Xing, Zhenchang Yitagesu, Sofonias Zhang, Xiaowang Feng, Zhiyong Sun, Jiamou Huang, Qing |
| contents | Textual Vulnerability Descriptions (TVDs) are crucial for security analysts to understand and address software vulnerabilities. However, the key aspect inconsistencies in TVDs from different repositories pose challenges for achieving a comprehensive understanding of vulnerabilities. Existing approaches aim to mitigate inconsistencies by aligning TVDs with external knowledge bases, but they often discard valuable information and fail to synthesize comprehensive representations. In this paper, we propose a domain-constrained LLM-based synthesis framework for unifying key aspects of TVDs. Our framework consists of three stages: 1) Extraction, guided by rule-based templates to ensure all critical details are captured; 2) Self-evaluation, using domain-specific anchor words to assess semantic variability across sources; and 3) Fusion, leveraging information entropy to reconcile inconsistencies and prioritize relevant details. This framework improves synthesis performance, increasing the F1 score for key aspect augmentation from 0.82 to 0.87, while enhancing comprehension and efficiency by over 30\%. We further develop Digest Labels, a practical tool for visualizing TVDs, which human evaluations show significantly boosts usability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_16123 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Domain-constrained Synthesis of Inconsistent Key Aspects in Textual Vulnerability Descriptions Han, Linyi Pan, Shidong Xing, Zhenchang Yitagesu, Sofonias Zhang, Xiaowang Feng, Zhiyong Sun, Jiamou Huang, Qing Software Engineering Textual Vulnerability Descriptions (TVDs) are crucial for security analysts to understand and address software vulnerabilities. However, the key aspect inconsistencies in TVDs from different repositories pose challenges for achieving a comprehensive understanding of vulnerabilities. Existing approaches aim to mitigate inconsistencies by aligning TVDs with external knowledge bases, but they often discard valuable information and fail to synthesize comprehensive representations. In this paper, we propose a domain-constrained LLM-based synthesis framework for unifying key aspects of TVDs. Our framework consists of three stages: 1) Extraction, guided by rule-based templates to ensure all critical details are captured; 2) Self-evaluation, using domain-specific anchor words to assess semantic variability across sources; and 3) Fusion, leveraging information entropy to reconcile inconsistencies and prioritize relevant details. This framework improves synthesis performance, increasing the F1 score for key aspect augmentation from 0.82 to 0.87, while enhancing comprehension and efficiency by over 30\%. We further develop Digest Labels, a practical tool for visualizing TVDs, which human evaluations show significantly boosts usability. |
| title | Domain-constrained Synthesis of Inconsistent Key Aspects in Textual Vulnerability Descriptions |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2511.16123 |