EUVIMEDEUVIMED entdecken
Crossref

Security Attacks on LLM-based Code Completion Tools

Wen Cheng, Ke Sun, Xinyu Zhang, Wei Wang

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (22) · 23669-23677

DOI: 10.1609/aaai.v39i22.34537 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Wen Cheng und 3 weiteren Autor:innen. Die Arbeit wurde bisher 17-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid development of large language models (LLMs) has significantly advanced code completion capabilities, giving rise to a new generation of LLM-based Code Completion Tools (LCCTs). Unlike general-purpose LLMs, these tools possess unique workflows, integrating multiple information sources as input and prioritizing code suggestions over natural language interaction, which introduces distinct security challenges. Additionally, LCCTs often rely on proprietary code datasets for training, raising concerns about the potential exposure of sensitive data. This paper exploits these distinct characteristics of LCCTs to develop targeted attack methodologies on two critical security risks: jailbreaking and training data extraction attacks. Our experimental results expose significant vulnerabilities within LCCTs, including a 99.4% success rate in jailbreaking attacks on GitHub Copilot and a 46.3% success rate on Amazon Q. Furthermore, We successfully extracted sensitive user data from GitHub Copilot, including 54 real email addresses and 314 physical addresses associated with GitHub usernames. Our study also demonstrates that these code-based attack methods are effective against general-purpose LLMs, highlighting a broader security misalignment in the handling of code by modern LLMs. These findings underscore critical security challenges associated with LCCTs and suggest essential directions for strengthening their security frameworks.

Zitieren

APA

Cheng, W., Sun, K., Zhang, X., & Wang, W. (2025). Security Attacks on LLM-based Code Completion Tools. Proceedings of the AAAI Conference on Artificial Intelligence, 39(22), 23669-23677. https://doi.org/10.1609/aaai.v39i22.34537

Vancouver

Cheng W, Sun K, Zhang X, Wang W. Security Attacks on LLM-based Code Completion Tools. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(22):23669-23677. doi:10.1609/aaai.v39i22.34537

BibTeX
@article{Cheng2025,
  author = {Cheng, Wen and Sun, Ke and Zhang, Xinyu and Wang, Wei},
  title = {Security Attacks on LLM-based Code Completion Tools},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {22},
  pages = {23669--23677},
  doi = {10.1609/aaai.v39i22.34537}
}
Kostenlos starten →