Large language models have enabled powerful code completion systems that assist developers by predicting subsequent lines of code. However, these models remain vulnerable to backdoor attacks, where malicious fine-tuning data covertly implants unsafe behaviors. Despite advances in defensive techniques, adaptive and sophisticated backdoor attacks still evade detection and mitigation.
We present CodeTracer, a forensic framework that traces malicious code completions back to the backdoor fine-tuning data responsible for them. Operating under realistic post-deployment constraints, CodeTracer relies solely on the fine-tuning corpus and the reported miscompletion event. It extracts a structured behavioral fingerprint from the compromised output, narrows the search to semantically relevant code samples, and employs LLM-based reasoning to attribute unsafe logic to specific backdoor data.
Extensive evaluations across three representative vulnerability cases and ten backdoor attacks demonstrate that CodeTracer consistently achieves high forensic accuracy, low false identification rates, and strong robustness against adaptive attacks.
Blogger's Review: The introduction of CodeTracer offers a fresh perspective on tracking backdoor attacks, especially in the context of the increasing prevalence of code completion systems. Its accuracy and robustness provide crucial security assurances for developers. The successful application of this framework may drive further research and practice in security, warranting close attention.