paperAugust 2026Unreviewed

Vulnerable Code Search: Transferable Attack for Code Language Models

Kaicheng Wang, Liyan Huang, Jesse Thomason, Weihang Wang

Abstract

Reliable code retrieval is crucial for developer productivity and effective code reuse. However, current neural code language models (CLMs) powering search tools are susceptible to adversarial attacks targeting non-functional textual elements. In this paper, we introduce a programming language-agnostic, transferable, adversarial attack that exploits this CLM vulnerability. Our approach perturbs identifiers within a code snippet without altering the snippet's functionality to artificially align t

Framework mappings

MITRE ATLAS

AML.T0043Craft Adversarial Data

Suggested from the entry's categories.

Cite

@misc{wang2026vulnerable,
  title = {{Vulnerable Code Search: Transferable Attack for Code Language Models}},
  author = {Kaicheng Wang and Liyan Huang and Jesse Thomason and Weihang Wang},
  year = {2026},
  month = aug,
  eprint = {2608.26031},
  archivePrefix = {arXiv},
  url = {https://www.semanticscholar.org/paper/fca4f64d2721d15004f8e9081a7b5dbb5e38620d}
}