Search papers, labs, and topics across Lattice.
This paper introduces a transferable adversarial attack targeting code language models (CLMs) that perturbs identifiers in code snippets without changing their functionality, effectively misaligning them with target queries. The method is shown to be effective even when applied using smaller models, achieving significant degradation in retrieval accuracy across various state-of-the-art systems. Key results reveal that this attack can reduce the Mean Reciprocal Rank (MRR) by up to 77%, highlighting the vulnerabilities in current code retrieval systems and the urgent need for more resilient solutions.
Adversarial attacks can mislead code search tools by altering identifiers, reducing retrieval accuracy by up to 77% without changing code functionality.
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 metrics such as the Mean Reciprocal Rank (MRR) of state-of-the-art models by up to 77%. The experimental results highlight the fragility of current code search methods and underscore the need for more robust, semantic-aware approaches.
