# Misleading Authorship Attribution of Source Code using Adversarial Learning

arXiv: https://arxiv.org/abs/1905.12386 · HTML: https://mlsanity.com/paper/1905.12386/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 May 2019.

## Built on by (most cited first, 30 of 33)

- [Locally Differentially Private Document Generation Using Zero Shot Prompting](https://mlsanity.com/paper/2310.16111/) (2023)
- ["Real Attackers Don't Compute Gradients": Bridging the Gap Between Adversarial ML Research and Practice](https://mlsanity.com/paper/2212.14315/) (2022)
- [An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection](https://mlsanity.com/paper/2406.06822/) (2024)
- [Bridging Pre-trained Models and Downstream Tasks for Source Code Understanding](https://mlsanity.com/paper/2112.02268/) (2021)
- [IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators](https://mlsanity.com/paper/2403.03894/) (2024)
- [Generating Adversarial Computer Programs using Optimized Obfuscations](https://mlsanity.com/paper/2103.11882/) (2021)
- [Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit](https://mlsanity.com/paper/2401.00288/) (2023)
- [Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-Art](https://mlsanity.com/paper/2112.12310/) (2021)
- [Code Needs Comments: Enhancing Code LLMs with Comment Augmentation](https://mlsanity.com/paper/2402.13013/) (2024)
- [RoPGen: Towards Robust Code Authorship Attribution via Automatic Coding Style Transformation](https://mlsanity.com/paper/2202.06043/) (2022)
- [Advising OpenMP Parallelization via a Graph-Based Approach with Transformers](https://mlsanity.com/paper/2305.11999/) (2023)
- [I Know Which LLM Wrote Your Code Last Summer: LLM generated Code Stylometry for Authorship Attribution](https://mlsanity.com/paper/2506.17323/) (2025)
- [No more Reviewer #2: Subverting Automatic Paper-Reviewer Assignment using Adversarial Learning](https://mlsanity.com/paper/2303.14443/) (2023)
- [Towards Making Deep Learning-based Vulnerability Detectors Robust](https://mlsanity.com/paper/2108.00669/) (2021)
- [Evaluation of Contrastive Learning with Various Code Representations for Code Clone Detection](https://mlsanity.com/paper/2206.08726/) (2022)
- [Adversary for Social Good: Leveraging Adversarial Attacks to Protect Personal Attribute Privacy](https://mlsanity.com/paper/2306.02488/) (2023)
- [Capture the Flags: Family-Based Evaluation of Agentic LLMs via Semantics-Preserving Transformations](https://mlsanity.com/paper/2602.05523/) (2026)
- [CLAWSAT: Towards Both Robust and Accurate Code Models](https://mlsanity.com/paper/2211.11711/) (2022)
- [SHIELD: Thwarting Code Authorship Attribution](https://mlsanity.com/paper/2304.13255/) (2023)
- [Semantic-Preserving Transformations as Mutation Operators: A Study on Their Effectiveness in Defect Detection](https://mlsanity.com/paper/2503.23448/) (2025)
- [On Technique Identification and Threat-Actor Attribution using LLMs and Embedding Models](https://mlsanity.com/paper/2505.11547/) (2025)
- [The Hidden DNA of LLM-Generated JavaScript: Structural Patterns Enable High-Accuracy Authorship Attribution](https://mlsanity.com/paper/2510.10493/) (2025)
- [Constrained Adaptive Attacks: Realistic Evaluation of Adversarial Examples and Robust Training of Deep Neural Networks for Tabular Data](https://mlsanity.com/paper/2311.04503/) (2023)
- [Adversarial Patterns: Building Robust Android Malware Classifiers](https://mlsanity.com/paper/2203.02121/) (2022)
- [I still know it's you! On Challenges in Anonymizing Source Code](https://mlsanity.com/paper/2208.12553/) (2022)
- [On the Effectiveness of Adversarial Samples against Ensemble Learning-based Windows PE Malware Detectors](https://mlsanity.com/paper/2309.13841/) (2023)
- [On the Detection of Image-Scaling Attacks in Machine Learning](https://mlsanity.com/paper/2310.15085/) (2023)
- [Untargeted Code Authorship Evasion with Seq2Seq Transformation](https://mlsanity.com/paper/2311.15366/) (2023)
- [AuthAttLyzer-V2: Unveiling Code Authorship Attribution using Enhanced Ensemble Learning Models & Generating Benchmark Dataset](https://mlsanity.com/paper/2406.19896/) (2024)
- [A Stylometric Application of Large Language Models](https://mlsanity.com/paper/2510.21958/) (2025)

## Abstract (arXiv)

In this paper, we present a novel attack against authorship attribution of source code. We exploit that recent attribution methods rest on machine learning and thus can be deceived by adversarial examples of source code. Our attack performs a series of semantics-preserving code transformations that mislead learning-based attribution but appear plausible to a developer. The attack is guided by Monte-Carlo tree search that enables us to operate in the discrete domain of source code. In an empirical evaluation with source code from 204 programmers, we demonstrate that our attack has a substantial effect on two recent attribution methods, whose accuracy drops from over 88% to 1% under attack. Furthermore, we show that our attack can imitate the coding style of developers with high accuracy and thereby induce false attributions. We conclude that current approaches for authorship attribution are inappropriate for practical application and there is a need for resilient analysis techniques.