paperJune 2026Unreviewed

Securing Code Understanding: Detecting Natural Backdoor Vulnerability in Code Language Models

Yuchen Chen, Weisong Sun, Haocheng Huang, Yuan Xiao, Chunrong Fang, Yiran Zhang, Tingting Xu, Zhenpeng Chen, An Guo, Peizhuo Lv, Xiaofang Zhang, Zhenyu Chen, Yang Liu, Baowen Xu

View resource PDF

Abstract

Code Language Models (CodeLMs) have become integral to software engineering, significantly advancing code intelligence tasks. However, their widespread adoption has raised critical security concerns, particularly regarding susceptibility to backdoor attacks. Recent studies have uncovered naturally occurring backdoors, referred to as natural backdoors, in normally trained deep learning models. Despite posing threats as serious as those introduced through data poisoning, security implications of n

Framework mappings

OWASP Top 10 for LLM Applications

LLM04Data and Model Poisoning

MITRE ATLAS

AML.T0020Poison Training Data

Suggested from the entry's categories.

Cite

@misc{chen2026securing,
  title = {{Securing Code Understanding: Detecting Natural Backdoor Vulnerability in Code Language Models}},
  author = {Yuchen Chen and Weisong Sun and Haocheng Huang and Yuan Xiao and Chunrong Fang and Yiran Zhang and Tingting Xu and Zhenpeng Chen and An Guo and Peizhuo Lv and Xiaofang Zhang and Zhenyu Chen and Yang Liu and Baowen Xu},
  year = {2026},
  month = jun,
  eprint = {2606.10846},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.10846}
}