Conference paper · 2026 · Open access

SOSecure: The Wisdom of the Crowd for Safer AI-Generated Code

MANISHA MUKHERJEE, Vincent Josua Hellendoorn

ACM International Conference on AI-Powered Software (AIware), 135–144 · Published 5 July 2026 · DOI 10.1145/3805760.3814903

Open full textCite this paper

In brief

“SOSecure: The Wisdom of the Crowd for Safer AI-Generated Code” is a 2026 conference paper by MANISHA MUKHERJEE and Vincent Josua Hellendoorn, published in ACM International Conference on AI-Powered Software (AIware). OpenAlex counts 1 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at ACM International Conference on AI-Powered Software (AIware).

Citations
1
Most cited in
2026 (1)
Field-weighted impact
1.32
References
27
Authors
2

Abstract

Large Language Models (LLMs) are widely used for automated code generation. Their reliance on infrequently updated pretraining data can leave them unaware of newly discovered vulnerabilities and evolving security standards, making them prone to producing insecure code. In contrast, developer communities on Stack Overflow (SO) provide an ever-evolving repository of knowledge, where security vulnerabilities are actively discussed and addressed through collective expertise. These community-driven insights remain largely untapped by LLMs. This paper introduces SOSecure, a Retrieval- Augmented Generation (RAG) system that leverages the collective security expertise found in SO discussions to improve the security of LLM-generated code. We build a security-focused knowledge base by extracting SO answers and comments that explicitly identify vulnerabilities. Unlike common uses of RAG, SOSecure triggers after code has been generated to find discussions that identify flaws in similar code. These are used in a prompt to an LLM to consider revising the code. Evaluation across three datasets (SALLM dataset, LLMSecEval, and LMSys) shows that SOSecure achieves strong fix rates of 71.7%, 91.3%, and 96.7% respectively, compared to prompting GPT-4 without relevant discussions (49.1%, 56.5%, and 37.5%), and outperforms multiple other baselines. SOSecure operates as a language-agnostic complement to existing LLMs, without requiring retraining or fine-tuning, making it easy to deploy. Our results underscore the importance of maintaining active developer forums,

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

MUKHERJEE, M., & Hellendoorn, V. J. (2026). SOSecure: The Wisdom of the Crowd for Safer AI-Generated Code. ACM International Conference on AI-Powered Software (AIware), 135–144. https://doi.org/10.1145/3805760.3814903

MLA 9

MUKHERJEE, MANISHA, and Vincent Josua Hellendoorn. “SOSecure: The Wisdom of the Crowd for Safer AI-Generated Code.” ACM International Conference on AI-Powered Software (AIware), 2026, pp. 135–144. https://doi.org/10.1145/3805760.3814903.

Chicago

MUKHERJEE, MANISHA and Vincent Josua Hellendoorn. 2026. “SOSecure: The Wisdom of the Crowd for Safer AI-Generated Code.” ACM International Conference on AI-Powered Software (AIware): 135–144. https://doi.org/10.1145/3805760.3814903.

Harvard

MUKHERJEE, M. and Hellendoorn, V. J. (2026) ‘SOSecure: The Wisdom of the Crowd for Safer AI-Generated Code’, ACM International Conference on AI-Powered Software (AIware), pp. 135–144. doi:10.1145/3805760.3814903.

IEEE

M. MUKHERJEE and V. J. Hellendoorn, “SOSecure: The Wisdom of the Crowd for Safer AI-Generated Code,” ACM International Conference on AI-Powered Software (AIware), pp. 135–144, 2026, doi: 10.1145/3805760.3814903.

BibTeX

@inproceedings{mukherjee2026sosecure,
  title     = {{SOSecure: The Wisdom of the Crowd for Safer AI-Generated Code}},
  author    = {MUKHERJEE, MANISHA and Hellendoorn, Vincent Josua},
  booktitle = {ACM International Conference on AI-Powered Software (AIware)},
  year      = {2026},
  pages     = {135--144},
  doi       = {10.1145/3805760.3814903},
  url       = {https://doi.org/10.1145/3805760.3814903}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Information Systems › Software Engineering Research

  • large language models
  • retrieval-augmented generation
  • Stack Overflow
  • security vulnerabilities
  • code vulnerability detection
  • knowledge base construction

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

MUKHERJEE, M., & Hellendoorn, V. J. (2026). SOSecure: The Wisdom of the Crowd for Safer AI-Generated Code. ACM International Conference on AI-Powered Software (AIware), 135–144. https://doi.org/10.1145/3805760.3814903

How many times has this paper been cited?

1 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 ACM International Conference on AI-Powered Software (AIware): sign in and open the full text from this page.

Who wrote this paper?

MANISHA MUKHERJEE, Vincent Josua Hellendoorn.

What is the DOI of this paper?

10.1145/3805760.3814903, permanently at https://doi.org/10.1145/3805760.3814903. 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.