Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2512.08326 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908700175761408 |
|---|---|
| author | Wang, Bin Li, Hui Zhang, Liyang Zhuang, Qijia Yang, Ao Zhang, Dong Luo, Xijun Lin, Bing |
| author_facet | Wang, Bin Li, Hui Zhang, Liyang Zhuang, Qijia Yang, Ao Zhang, Dong Luo, Xijun Lin, Bing |
| contents | Sensitive information leakage in code repositories has emerged as a critical security challenge. Traditional detection methods that rely on regular expressions, fingerprint features, and high-entropy calculations often suffer from high false-positive rates. This not only reduces detection efficiency but also significantly increases the manual screening burden on developers. Recent advances in large language models (LLMs) and multi-agent collaborative architectures have demonstrated remarkable potential for tackling complex tasks, offering a novel technological perspective for sensitive information detection. In response to these challenges, we propose Argus, a multi-agent collaborative framework for detecting sensitive information. Argus employs a three-tier detection mechanism that integrates key content, file context, and project reference relationships to effectively reduce false positives and enhance overall detection accuracy. To comprehensively evaluate Argus in real-world repository environments, we developed two new benchmarks, one to assess genuine leak detection capabilities and another to evaluate false-positive filtering performance. Experimental results show that Argus achieves up to 94.86% accuracy in leak detection, with a precision of 96.36%, recall of 94.64%, and an F1 score of 0.955. Moreover, the analysis of 97 real repositories incurred a total cost of only 2.2$. All code implementations and related datasets are publicly available at https://github.com/TheBinKing/Argus-Guard for further research and application. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_08326 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Argus: A Multi-Agent Sensitive Information Leakage Detection Framework Based on Hierarchical Reference Relationships Wang, Bin Li, Hui Zhang, Liyang Zhuang, Qijia Yang, Ao Zhang, Dong Luo, Xijun Lin, Bing Cryptography and Security Artificial Intelligence Sensitive information leakage in code repositories has emerged as a critical security challenge. Traditional detection methods that rely on regular expressions, fingerprint features, and high-entropy calculations often suffer from high false-positive rates. This not only reduces detection efficiency but also significantly increases the manual screening burden on developers. Recent advances in large language models (LLMs) and multi-agent collaborative architectures have demonstrated remarkable potential for tackling complex tasks, offering a novel technological perspective for sensitive information detection. In response to these challenges, we propose Argus, a multi-agent collaborative framework for detecting sensitive information. Argus employs a three-tier detection mechanism that integrates key content, file context, and project reference relationships to effectively reduce false positives and enhance overall detection accuracy. To comprehensively evaluate Argus in real-world repository environments, we developed two new benchmarks, one to assess genuine leak detection capabilities and another to evaluate false-positive filtering performance. Experimental results show that Argus achieves up to 94.86% accuracy in leak detection, with a precision of 96.36%, recall of 94.64%, and an F1 score of 0.955. Moreover, the analysis of 97 real repositories incurred a total cost of only 2.2$. All code implementations and related datasets are publicly available at https://github.com/TheBinKing/Argus-Guard for further research and application. |
| title | Argus: A Multi-Agent Sensitive Information Leakage Detection Framework Based on Hierarchical Reference Relationships |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2512.08326 |