{"ID":2826186,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.19215","arxiv_id":"2512.19215","title":"Semantically-Equivalent Transformations-Based Backdoor Attacks against Neural Code Models: Characterization and Mitigation","abstract":"Neural code models have been increasingly incorporated into software development processes. However, their susceptibility to backdoor attacks presents a significant security risk. The state-of-the-art understanding focuses on injection-based attacks, which insert anomalous patterns into software code. These attacks can be neutralized by standard sanitization techniques. This status quo may lead to a false sense of security regarding backdoor attacks. In this paper, we introduce a new kind of backdoor attacks, dubbed Semantically-Equivalent Transformation (SET)-based backdoor attacks, which use semantics-preserving low-prevalence code transformations to generate stealthy triggers. We propose a framework to guide the generation of such triggers. Our experiments across five tasks, six languages, and models like CodeBERT, CodeT5, and StarCoder show that SET-based attacks achieve high success rates (often \u003e90%) while preserving model utility. The attack proves highly stealthy, evading state-of-the-art defenses with detection rates on average over 25.13% lower than injection-based counterparts. We evaluate normalization-based countermeasures and find they offer only partial mitigation, confirming the attack's robustness. These results motivate further investigation into scalable defenses tailored to SET-based attacks.","short_abstract":"Neural code models have been increasingly incorporated into software development processes. However, their susceptibility to backdoor attacks presents a significant security risk. The state-of-the-art understanding focuses on injection-based attacks, which insert anomalous patterns into software code. These attacks can...","url_abs":"https://arxiv.org/abs/2512.19215","url_pdf":"https://arxiv.org/pdf/2512.19215v1","authors":"[\"Junyao Ye\",\"Zhen Li\",\"Xi Tang\",\"Shouhuai Xu\",\"Deqing Zou\",\"Zhongsheng Yuan\"]","published":"2025-12-22T09:54:52Z","proceeding":"cs.SE","tasks":"[\"cs.SE\"]","methods":"[]","has_code":false}