mlsanityData to 14 Oct 2026

Misleading Authorship Attribution of Source Code using Adversarial Learning

arXiv 1905.12386 ↗First posted 29 May 2019cs.LG cs.CR stat.MLcited by 33

Not on the map. Why?

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.

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

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 4; 2022: 6; 2023: 10; 2024: 4; 2025: 5; 2026: 4.

33 papers.

Sort:

By area:

  1. 2023Locally Differentially Private Document Generation Using Zero Shot Promptingcited by 63
  2. 2022"Real Attackers Don't Compute Gradients": Bridging the Gap Between Adversarial ML Research and Practicecited by 56
  3. 2024An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detectioncited by 40
  4. 2021Bridging Pre-trained Models and Downstream Tasks for Source Code Understandingcited by 28
  5. 2024IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generatorscited by 23
  6. 2021Generating Adversarial Computer Programs using Optimized Obfuscationscited by 22
  7. 2023Deep Learning for Code Intelligence: Survey, Benchmark and Toolkitcited by 22
  8. 2021Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-Artcited by 18
  9. 2024Code Needs Comments: Enhancing Code LLMs with Comment Augmentationcited by 16
  10. 2022RoPGen: Towards Robust Code Authorship Attribution via Automatic Coding Style Transformationcited by 15
  11. 2023Advising OpenMP Parallelization via a Graph-Based Approach with Transformerscited by 10
  12. 2025I Know Which LLM Wrote Your Code Last Summer: LLM generated Code Stylometry for Authorship Attributioncited by 9
21 more
  1. 2023No more Reviewer #2: Subverting Automatic Paper-Reviewer Assignment using Adversarial Learningcited by 7
  2. 2021Towards Making Deep Learning-based Vulnerability Detectors Robustcited by 4
  3. 2022Evaluation of Contrastive Learning with Various Code Representations for Code Clone Detectioncited by 3
  4. 2023Adversary for Social Good: Leveraging Adversarial Attacks to Protect Personal Attribute Privacycited by 3
  5. 2026Capture the Flags: Family-Based Evaluation of Agentic LLMs via Semantics-Preserving Transformationscited by 3
  6. 2022CLAWSAT: Towards Both Robust and Accurate Code Modelscited by 2
  7. 2023SHIELD: Thwarting Code Authorship Attributioncited by 2
  8. 2025Semantic-Preserving Transformations as Mutation Operators: A Study on Their Effectiveness in Defect Detectioncited by 2
  9. 2025On Technique Identification and Threat-Actor Attribution using LLMs and Embedding Modelscited by 2
  10. 2025The Hidden DNA of LLM-Generated JavaScript: Structural Patterns Enable High-Accuracy Authorship Attributioncited by 2
  11. 2023Constrained Adaptive Attacks: Realistic Evaluation of Adversarial Examples and Robust Training of Deep Neural Networks for Tabular Datacited by 1
  12. 2022Adversarial Patterns: Building Robust Android Malware Classifierscited by 0
  13. 2022I still know it's you! On Challenges in Anonymizing Source Codecited by 0
  14. 2023On the Effectiveness of Adversarial Samples against Ensemble Learning-based Windows PE Malware Detectorscited by 0
  15. 2023On the Detection of Image-Scaling Attacks in Machine Learningcited by 0
  16. 2023Untargeted Code Authorship Evasion with Seq2Seq Transformationcited by 0
  17. 2024AuthAttLyzer-V2: Unveiling Code Authorship Attribution using Enhanced Ensemble Learning Models & Generating Benchmark Datasetcited by 0
  18. 2025A Stylometric Application of Large Language Modelscited by 0
  19. 2026Stylometric Defenses Against Author Impersonation in Software Repositoriescited by 0
  20. 2026REPLICANT: Learning Policies for Evading and Hardening Malware Detectorscited by 0
  21. 2026Style, Not Self: Surface Cues Explain Zero-Shot Code Attribution by Large Language Modelscited by 0