Conference paper · 2025 · Open access
APILOT: Improving the Security and Usability of LLM Code Suggestions via Outdated API Mitigation
Annual Computer Security Applications Conference, 1193–1208 · Published 8 December 2025 · DOI 10.1109/acsac67867.2025.00094
In brief
“APILOT: Improving the Security and Usability of LLM Code Suggestions via Outdated API Mitigation” is a 2025 conference paper by Weiheng Bai and 6 co-authors, published in Annual Computer Security Applications Conference. OpenAlex counts 17 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 17
- Most cited in
- 2026 (13)
- Field-weighted impact
- 5.40
- References
- 39
- Authors
- 7
Abstract
With the rapid development of large language models (LLMs), their applications have expanded into diverse fields, such as code assistance. However, the substantial size of LLMs makes their training highly resource- and time-consuming, which leads to lengthy retraining and delayed updating. Consequently, LLMs trained based on old data may generate outdated results. This becomes extremely critical in the scenario of avoiding vulnerabilities. New vulnerabilities are discovered every day. Without updating their knowledge, LLMs may inadvertently generate code that includes these newly discovered vulnerabilities. Current strategies, such as prompt engineering and fine-tuning, do not effectively address this issue. Prompt engineering fails to equip LLMs with comprehensive, up-to-date knowledge, while fine-tuning remains prohibitively resource-intensive and time-consuming. To address this issue, we study the problem of LLM recommending outdated APIs and propose a new solution, named APILOT, which maintains a real-time, quickly updatable dataset of outdated APIs. Additionally, APILOT utilizes pre-constructed cache prediction and augmented generation methods that leverage this dataset to navigate LLMs in generating secure, version-aware code. We conducted a comprehensive empirical evaluation of APILOT across seventeen state-of-the-art large language models (LLMs), including both open-source and commercial systems. The results demonstrate that APILOT reduces outdated API recommendations by an average of 75%, with some models achieving up to 100% mitigation in specific large language models. Notably, these improvements are achieved with minimal performance overhead. Interestingly, while enhancing security, APILOT also improves the usability of LLM -generated code by an average of 37%, with gains reaching up to 85.6% in certain large language models. Importantly, these improvements are achieved without compromising code functionality, as measured by ICE-SCORE evaluations across diverse prompts and LLMs. This demonstrates APILOT's dual benefit─it not only reduces the risk of outdated API usage but also enhances the practical utility and deployability of generated code. Together, these results highlight APILOT 's potential to improve both security and developer experience in real-world AI-assisted programming environments.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Bai, W., Ke, X., Huang, P., Wu, Q., Wen, J., Wu, J., & Lu, K. (2025). APILOT: Improving the Security and Usability of LLM Code Suggestions via Outdated API Mitigation. Annual Computer Security Applications Conference, 1193–1208. https://doi.org/10.1109/acsac67867.2025.00094
MLA 9
Bai, Weiheng, et al. “APILOT: Improving the Security and Usability of LLM Code Suggestions via Outdated API Mitigation.” Annual Computer Security Applications Conference, 2025, pp. 1193–1208. https://doi.org/10.1109/acsac67867.2025.00094.
Chicago
Bai, Weiheng, Xuan Ke, Pengxiang Huang, Qiushi Wu, Jianing Wen, Jingjing Wu, and Kangjie Lu. 2025. “APILOT: Improving the Security and Usability of LLM Code Suggestions via Outdated API Mitigation.” Annual Computer Security Applications Conference: 1193–1208. https://doi.org/10.1109/acsac67867.2025.00094.
Harvard
Bai, W. et al. (2025) ‘APILOT: Improving the Security and Usability of LLM Code Suggestions via Outdated API Mitigation’, Annual Computer Security Applications Conference, pp. 1193–1208. doi:10.1109/acsac67867.2025.00094.
IEEE
W. Bai et al., “APILOT: Improving the Security and Usability of LLM Code Suggestions via Outdated API Mitigation,” Annual Computer Security Applications Conference, pp. 1193–1208, 2025, doi: 10.1109/acsac67867.2025.00094.
BibTeX
@inproceedings{bai2025apilot,
title = {{APILOT: Improving the Security and Usability of LLM Code Suggestions via Outdated API Mitigation}},
author = {Bai, Weiheng and Ke, Xuan and Huang, Pengxiang and Wu, Qiushi and Wen, Jianing and Wu, Jingjing and Lu, Kangjie},
booktitle = {Annual Computer Security Applications Conference},
year = {2025},
pages = {1193--1208},
doi = {10.1109/acsac67867.2025.00094},
url = {https://doi.org/10.1109/acsac67867.2025.00094}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2024 | 1 | |
| 2025 | 3 | |
| 2026 | 13 |
Its field-weighted citation impact is 5.40: it has been cited 5.40 times as often as the average work of the same field, type and year (1.00 is the world average).
Topic and keywords
Physical Sciences › Computer Science › Information Systems › Software Engineering Research
- large language models
- software vulnerabilities
- code security
- AI-assisted programming
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Bai, W., Ke, X., Huang, P., Wu, Q., Wen, J., Wu, J., & Lu, K. (2025). APILOT: Improving the Security and Usability of LLM Code Suggestions via Outdated API Mitigation. Annual Computer Security Applications Conference, 1193–1208. https://doi.org/10.1109/acsac67867.2025.00094
How many times has this paper been cited?
17 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.
Who wrote this paper?
Weiheng Bai, Xuan Ke, Pengxiang Huang, Qiushi Wu, Jianing Wen, Jingjing Wu, Kangjie Lu.
What is the DOI of this paper?
10.1109/acsac67867.2025.00094, permanently at https://doi.org/10.1109/acsac67867.2025.00094. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.