Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

7-2026

Abstract

The widespread availability of large-scale code datasets has accelerated the development of code large language models (CodeLLMs), raising concerns about unauthorized dataset usage. Dataset poisoning offers a proactive defense by reducing the utility of such unauthorized training. However, existing poisoning methods often require full-dataset poisoning and introduce transformations that break code compilability. In this paper, we introduce FunPoison, a functionality-preserving poisoning approach that injects short, compilable weak-use fragments into executed code paths. FunPoison leverages reusable statement-level templates with automatic repair and conservative safety checking to ensure side-effect freedom, while a type-aware synthesis module preserves type correctness, suppresses static-analysis warnings, and improves stealth. Extensive experiments across multiple CodeLLMs and code-generation benchmarks show that FunPoison achieves effective poisoning by contaminating only 10% of the dataset, while maintaining 100% compilability and functional correctness. FunPoison also remains robust against advanced code sanitization techniques, including detection, purification, rewriting, static-analysis, and formatting defenses.

Discipline

Artificial Intelligence and Robotics | Software Engineering

Research Areas

Software and Cyber-Physical Systems

Areas of Excellence

Digital transformation

Publication

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), San Diego, California, July 2-7

First Page

31284

Last Page

31303

Identifier

10.18653/v1/2026.findings-acl.1564

Publisher

ACL

City or Country

San Diego, California

Additional URL

https://doi.org/10.18653/v1/2026.findings-acl.1564

Download

Share

COinS