Towards Classifying Benign And Malicious Packages Using Machine Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911276012142592 |
|---|---|
| author | Nguyen, Thanh-Cong Nguyen, Ngoc-Thanh Ung, Van-Giau Vu, Duc-Ly |
| author_facet | Nguyen, Thanh-Cong Nguyen, Ngoc-Thanh Ung, Van-Giau Vu, Duc-Ly |
| contents | Recently, the number of malicious open-source packages in package repositories has been increasing dramatically. While major security scanners focus on identifying known Common Vulnerabilities and Exposures (CVEs) in open-source packages, there are very few studies on detecting malicious packages. Malicious open-source package detection typically requires static, dynamic analysis, or both. Dynamic analysis is more effective as it can expose a package's behaviors at runtime. However, current dynamic analysis tools (e.g., ossf's package-analysis) lack an automatic method to differentiate malicious packages from benign packages. In this paper, we propose an approach to extract the features from dynamic analysis (e.g., executed commands) and leverage machine learning techniques to automatically classify packages as benign or malicious. Our evaluation of nearly 2000 packages on npm shows that the machine learning classifier achieves an AUC of 0.91 with a false positive rate of nearly 0%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_15033 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Classifying Benign And Malicious Packages Using Machine Learning Nguyen, Thanh-Cong Nguyen, Ngoc-Thanh Ung, Van-Giau Vu, Duc-Ly Cryptography and Security Recently, the number of malicious open-source packages in package repositories has been increasing dramatically. While major security scanners focus on identifying known Common Vulnerabilities and Exposures (CVEs) in open-source packages, there are very few studies on detecting malicious packages. Malicious open-source package detection typically requires static, dynamic analysis, or both. Dynamic analysis is more effective as it can expose a package's behaviors at runtime. However, current dynamic analysis tools (e.g., ossf's package-analysis) lack an automatic method to differentiate malicious packages from benign packages. In this paper, we propose an approach to extract the features from dynamic analysis (e.g., executed commands) and leverage machine learning techniques to automatically classify packages as benign or malicious. Our evaluation of nearly 2000 packages on npm shows that the machine learning classifier achieves an AUC of 0.91 with a false positive rate of nearly 0%. |
| title | Towards Classifying Benign And Malicious Packages Using Machine Learning |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2511.15033 |