Code Fingerprints: Disentangled Attribution of LLM-Generated Code
The rapid adoption of Large Language Models (LLMs) has transformed modern software development by enabling automated code generation at scale. While these systems improve productivity, they introduce new challenges for software governance, accountability, and compliance. Existing research primarily focuses on distinguishing machine-generated code from human-written code; however, many practical scenarios--such as vulnerability triage, incident investigation, and licensing audits--require identifying which LLM produced a given code snippet. In this paper, we study the problem of model-level code attribution, which aims to determine the source LLM responsible for generated code. Although attribution is challenging, differences in training data, architectures, alignment strategies, and decoding mechanisms introduce model-dependent stylistic and structural variations that serve as generative fingerprints. Leveraging this observation, we propose the Disentangled Code Attribution Network (DCAN), which separates Source-Agnostic semantic information from Source-Specific stylistic representations. Through a contrastive learning objective, DCAN isolates discriminative model-dependent signals while preserving task semantics, enabling multi-class attribution across models and programming languages. To support systematic evaluation, we construct the first large-scale benchmark dataset comprising code generated by four widely used LLMs (DeepSeek, Claude, Qwen, and ChatGPT) across four programming languages (Python, Java, C, and Go). Experimental results demonstrate that DCAN achieves reliable attribution performance across diverse settings, highlighting the feasibility of model-level provenance analysis in software engineering contexts. The dataset and implementation are publicly available at https://github.com/mtt500/DCAN.
Code (0)
등록된 구현이 없습니다.
Tasks
Contrastive LearningCode GenerationSimilar Papers 제목 키워드 기반
Model Attribution and Detection of Synthetic Speech via Vocoder Fingerprints
As speech generation technology advances, so do the potential threats of misusing synthetic speech signals. This work tackles three tasks: (1) single-model attribution in an open-world setting corresponding to the task o…
Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints
Recent advances in Generative Adversarial Networks (GANs) have shown increasing success in generating photorealistic images. But they also raise challenges to visual forensics and model attribution. We present the first …
Image AttributionImage GenerationCausal Fingerprints of AI Generative Models
AI generative models leave implicit traces in their generated images, which are commonly referred to as model fingerprints and are exploited for source attribution. Prior methods rely on model-specific cues or synthesis …
Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data
Photorealistic image generation has reached a new level of quality due to the breakthroughs of generative adversarial networks (GANs). Yet, the dark side of such deepfakes, the malicious use of generated media, raises co…
DeepFake DetectionFace SwappingImage GenerationMisinformationSmudged Fingerprints: A Systematic Evaluation of the Robustness of AI Image Fingerprints
Model fingerprint detection has shown promise to trace the provenance of AI-generated images in forensic applications. However, despite the inherent adversarial nature of these applications, existing evaluations rarely c…