Vulnerable Code Search: Transferable Attack for Code Language Models
[Inżynieria oprogramowania] Autorzy: Kaicheng Wang, Liyan Huang, Jesse Thomason i 1 więcej
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 the code with a target query. We demonstrate that our attack, even when computed using smaller code embedding models, such as CodeT5+, is highly effective and transferable to larger, closed-source embedding models, like Voyage-code-3, or LLMs like Gemini-3.1-Pro. Our attack can increase the similarity between the query and arbitrary, irrelevant code snippets, consequently degrading key retrieval m…
- Kategoria arxiv
- cs.SE
- Kategoria
- Inżynieria oprogramowania