EUVIMEDEUVIMED entdecken
Crossref

Semantically-Equivalent Transformations-Based Backdoor Attacks against Neural Code Models: Characterization and Mitigation

Junyao Ye, Zhen Li, Xi Tang, Shouhuai Xu, Deqing Zou, Zhongsheng Yuan, Hai Jin

ACM Transactions on Software Engineering and Methodology · 17.08.2026

DOI: 10.1145/3840391 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Software Engineering and Methodology, online erschienen am 17.08.2026. Verfasst von Junyao Ye und 6 weiteren Autor:innen. Die Arbeit nennt 76 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Neural code models are increasingly embedded in software development workflows, but their susceptibility to backdoor attacks presents a significant security risk. Existing studies have mainly examined injection-based attacks, which insert anomalous patterns into code and can often be weakened by standard sanitization and screening. This focus may create a false sense of security regarding backdoor attacks. In this paper, we introduce Semantically-Equivalent Transformation (SET)-based backdoor attacks, a new class of attacks that use semantics-preserving low-prevalence code transformations to generate stealthy triggers. We further propose Stylistic Pattern Backdoor Triggers (SPBT), a framework for constructing and prioritizing such triggers. Our experiments across five tasks and six languages, using models including CodeBERT, CodeT5, and StarCoder, show that SET-based attacks achieve attack success rates comparable to injection-based counterparts while preserving model utility. More importantly, SET-based attacks proved difficult for the evaluated automated defenses and human inspectors to detect, showing substantially lower detectability than injection-based counterparts. We evaluate normalization-based countermeasures and find they offer only partial mitigation. These results motivate further investigation into scalable defenses tailored to SET-based attacks.

Zitieren

APA

Ye, J., Li, Z., Tang, X., Xu, S., Zou, D., Yuan, Z., & Jin, H. (2026). Semantically-Equivalent Transformations-Based Backdoor Attacks against Neural Code Models: Characterization and Mitigation. ACM Transactions on Software Engineering and Methodology. https://doi.org/10.1145/3840391

Vancouver

Ye J, Li Z, Tang X, Xu S, Zou D, Yuan Z, et al. Semantically-Equivalent Transformations-Based Backdoor Attacks against Neural Code Models: Characterization and Mitigation. ACM Transactions on Software Engineering and Methodology. 2026. doi:10.1145/3840391

BibTeX
@article{Ye2026,
  author = {Ye, Junyao and Li, Zhen and Tang, Xi and Xu, Shouhuai and Zou, Deqing and Yuan, Zhongsheng and Jin, Hai},
  title = {Semantically-Equivalent Transformations-Based Backdoor Attacks against Neural Code Models: Characterization and Mitigation},
  journal = {ACM Transactions on Software Engineering and Methodology},
  year = {2026},
  doi = {10.1145/3840391}
}
Kostenlos starten →