{"ID":2831072,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.08326","arxiv_id":"2512.08326","title":"Argus: A Multi-Agent Sensitive Information Leakage Detection Framework Based on Hierarchical Reference Relationships","abstract":"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.","short_abstract":"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 significan...","url_abs":"https://arxiv.org/abs/2512.08326","url_pdf":"https://arxiv.org/pdf/2512.08326v1","authors":"[\"Bin Wang\",\"Hui Li\",\"Liyang Zhang\",\"Qijia Zhuang\",\"Ao Yang\",\"Dong Zhang\",\"Xijun Luo\",\"Bing Lin\"]","published":"2025-12-09T07:42:10Z","proceeding":"cs.CR","tasks":"[\"cs.CR\",\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":606092,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2831072,"paper_url":"https://arxiv.org/abs/2512.08326","paper_title":"Argus: A Multi-Agent Sensitive Information Leakage Detection Framework Based on Hierarchical Reference Relationships","repo_url":"https://github.com/TheBinKing/Argus-Guard","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}