Hybrid Privacy Policy-Code Consistency Check using Knowledge Graphs and LLMs
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_ | 1866912380755116032 |
|---|---|
| author | Mao, Zhenyu Fan, Xinxin Wang, Yifei Keung, Jacky Li, Jialong |
| author_facet | Mao, Zhenyu Fan, Xinxin Wang, Yifei Keung, Jacky Li, Jialong |
| contents | The increasing concern in user privacy misuse has accelerated research into checking consistencies between smartphone apps' declared privacy policies and their actual behaviors. Recent advances in Large Language Models (LLMs) have introduced promising techniques for semantic comparison, but these methods often suffer from low accuracies and expensive computational costs. To address this problem, this paper proposes a novel hybrid approach that integrates 1) knowledge graph-based deterministic checking to ensure higher accuracy, and 2) LLMs exclusively used for preliminary semantic analysis to save computational costs. Preliminary evaluation indicates this hybrid approach not only achieves 37.63% increase in precision and 23.13% increase F1-score but also consumes 93.5% less tokens and 87.3% shorter time. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_11502 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hybrid Privacy Policy-Code Consistency Check using Knowledge Graphs and LLMs Mao, Zhenyu Fan, Xinxin Wang, Yifei Keung, Jacky Li, Jialong Cryptography and Security Software Engineering The increasing concern in user privacy misuse has accelerated research into checking consistencies between smartphone apps' declared privacy policies and their actual behaviors. Recent advances in Large Language Models (LLMs) have introduced promising techniques for semantic comparison, but these methods often suffer from low accuracies and expensive computational costs. To address this problem, this paper proposes a novel hybrid approach that integrates 1) knowledge graph-based deterministic checking to ensure higher accuracy, and 2) LLMs exclusively used for preliminary semantic analysis to save computational costs. Preliminary evaluation indicates this hybrid approach not only achieves 37.63% increase in precision and 23.13% increase F1-score but also consumes 93.5% less tokens and 87.3% shorter time. |
| title | Hybrid Privacy Policy-Code Consistency Check using Knowledge Graphs and LLMs |
| topic | Cryptography and Security Software Engineering |
| url | https://arxiv.org/abs/2505.11502 |