# I Know Which LLM Wrote Your Code Last Summer: LLM generated Code Stylometry for Authorship Attribution

arXiv: https://arxiv.org/abs/2506.17323 · HTML: https://mlsanity.com/paper/2506.17323/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 68 references that are in the map.
- First posted on arXiv 18 Jun 2025.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [GraphCodeBERT: Pre-training Code Representations with Data Flow](https://mlsanity.com/paper/2009.08366/) (2020)
- [code2vec: Learning Distributed Representations of Code](https://mlsanity.com/paper/1803.09473/) (2018)
- [How Secure is Code Generated by ChatGPT?](https://mlsanity.com/paper/2304.09655/) (2023)
- [Authorship Attribution in the Era of LLMs: Problems, Methodologies, and Challenges](https://mlsanity.com/paper/2408.08946/) (2024)
- [Explainable Authorship Verification in Social Media via Attention-based Similarity Learning](https://mlsanity.com/paper/1910.08144/) (2019)
- [Misleading Authorship Attribution of Source Code using Adversarial Learning](https://mlsanity.com/paper/1905.12386/) (2019)
- [How secure is AI-generated Code: A Large-Scale Comparison of Large Language Models](https://mlsanity.com/paper/2404.18353/) (2024)
- [A Survey of AI-generated Text Forensic Systems: Detection, Attribution, and Characterization](https://mlsanity.com/paper/2403.01152/) (2024)
- [Assessing AI Detectors in Identifying AI-Generated Code: Implications for Education](https://mlsanity.com/paper/2401.03676/) (2024)
- [When Coding Style Survives Compilation: De-anonymizing Programmers from Executable Binaries](https://mlsanity.com/paper/1512.08546/) (2015)
- [Marking Code Without Breaking It: Code Watermarking for Detecting LLM-Generated Code](https://mlsanity.com/paper/2502.18851/) (2025)
- [Is The Watermarking Of LLM-Generated Code Robust?](https://mlsanity.com/paper/2403.17983/) (2024)
- [BinMLM: Binary Authorship Verification with Flow-aware Mixture-of-Shared Language Model](https://mlsanity.com/paper/2203.04472/) (2022)
- [I Can Find You in Seconds! Leveraging Large Language Models for Code Authorship Attribution](https://mlsanity.com/paper/2501.08165/) (2025)
- [CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs](https://mlsanity.com/paper/2506.11059/) (2025)
- [Detection of LLM-Paraphrased Code and Identification of the Responsible LLM Using Coding Style Features](https://mlsanity.com/paper/2502.17749/) (2025)
- [CodeVision: Detecting LLM-Generated Code Using 2D Token Probability Maps and Vision Models](https://mlsanity.com/paper/2501.03288/) (2025)
- [Dev2vec: Representing Domain Expertise of Developers in an Embedding Space](https://mlsanity.com/paper/2207.05132/) (2022)
- [Detection of LLM-Generated Java Code Using Discretized Nested Bigrams](https://mlsanity.com/paper/2502.15740/) (2025)

## Built on by (most cited first, 9 of 9)

- [The Hidden DNA of LLM-Generated JavaScript: Structural Patterns Enable High-Accuracy Authorship Attribution](https://mlsanity.com/paper/2510.10493/) (2025)
- [Agent trajectories as programs: fingerprinting and programming coding-agent behavior](https://mlsanity.com/paper/2606.16988/) (2026)
- [Fingerprinting AI Coding Agents on GitHub](https://mlsanity.com/paper/2601.17406/) (2026)
- [Large Language Models and Forensic Linguistics: Navigating Opportunities and Threats in the Age of Generative AI](https://mlsanity.com/paper/2512.06922/) (2025)
- [GoCoMA: Hyperbolic Multimodal Representation Fusion for Large Language Model-Generated Code Attribution](https://mlsanity.com/paper/2604.16377/) (2026)
- [Saying More Than They Know: A Framework for Quantifying Epistemic-Rhetorical Miscalibration in Large Language Models](https://mlsanity.com/paper/2604.19768/) (2026)
- [AgenTag: Attribution of AI Coding Agents from Behavioral Fingerprints](https://mlsanity.com/paper/2608.00966/) (2026)
- [Token Signatures of Code: Comparing Coding Behaviors Across Large Language Models](https://mlsanity.com/paper/2609.22097/) (2026)
- [System Attribution in LLM Brand Recommendations: Single Responses Identify the System, Aggregated Brand Profiles Do Not Transfer](https://mlsanity.com/paper/2610.00253/) (2026)

## Abstract (arXiv)

Detecting AI-generated code, deepfakes, and other synthetic content is an emerging research challenge. As code generated by Large Language Models (LLMs) becomes more common, identifying the specific model behind each sample is increasingly important. This paper presents the first systematic study of LLM authorship attribution for C programs. We released CodeT5-Authorship, a novel model that uses only the encoder layers from the original CodeT5 encoder-decoder architecture, discarding the decoder to focus on classification. Our model's encoder output (first token) is passed through a two-layer classification head with GELU activation and dropout, producing a probability distribution over possible authors. To evaluate our approach, we introduce LLM-AuthorBench, a benchmark of 32,000 compilable C programs generated by eight state-of-the-art LLMs across diverse tasks. We compare our model to seven traditional ML classifiers and eight fine-tuned transformer models, including BERT, RoBERTa, CodeBERT, ModernBERT, DistilBERT, DeBERTa-V3, Longformer, and LoRA-fine-tuned Qwen2-1.5B. In binary classification, our model achieves 97.56% accuracy in distinguishing C programs generated by closely related models such as GPT-4.1 and GPT-4o, and 95.40% accuracy for multi-class attribution among five leading LLMs (Gemini 2.5 Flash, Claude 3.5 Haiku, GPT-4.1, Llama 3.3, and DeepSeek-V3). To support open science, we release the CodeT5-Authorship architecture, the LLM-AuthorBench benchmark, and all relevant Google Colab scripts on GitHub: https://github.com/LLMauthorbench/.