# Challenging Machine Learning-based Clone Detectors via Semantic-preserving Code Transformations

arXiv: https://arxiv.org/abs/2111.10793 · HTML: https://mlsanity.com/paper/2111.10793/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Nov 2021.

## Built on by (most cited first, 15 of 15)

- [CodeMark: Imperceptible Watermarking for Code Datasets against Neural Code Completion Models](https://mlsanity.com/paper/2308.14401/) (2023)
- [Can LLMs Reason About Program Semantics? A Comprehensive Evaluation of LLMs on Formal Specification Inference](https://mlsanity.com/paper/2503.04779/) (2025)
- [Pitfalls in Language Models for Code Intelligence: A Taxonomy and Survey](https://mlsanity.com/paper/2310.17903/) (2023)
- [Towards Reliable Evaluation of Neural Program Repair with Natural Robustness Testing](https://mlsanity.com/paper/2402.11892/) (2024)
- [Detection of LLM-Paraphrased Code and Identification of the Responsible LLM Using Coding Style Features](https://mlsanity.com/paper/2502.17749/) (2025)
- [NeuDep: Neural Binary Memory Dependence Analysis](https://mlsanity.com/paper/2210.02853/) (2022)
- [Adversarial Attacks against Binary Similarity Systems](https://mlsanity.com/paper/2303.11143/) (2023)
- [Revisiting Pre-trained Language Models for Vulnerability Detection](https://mlsanity.com/paper/2507.16887/) (2025)
- [HogVul: Black-box Adversarial Code Generation Framework Against LM-based Vulnerability Detectors](https://mlsanity.com/paper/2601.05587/) (2026)
- [LLM App Squatting and Cloning](https://mlsanity.com/paper/2411.07518/) (2024)
- [On the Lack of Robustness of Binary Function Similarity Systems](https://mlsanity.com/paper/2412.04163/) (2024)
- [Auto-SPT: Automating Semantic Preserving Transformations for Code](https://mlsanity.com/paper/2512.06042/) (2025)
- [Feedback Loops and Code Perturbations in LLM-based Software Engineering: A Case Study on a C-to-Rust Translation System](https://mlsanity.com/paper/2512.02567/) (2025)
- [How Do Semantically Equivalent Code Transformations Impact Membership Inference on LLMs for Code?](https://mlsanity.com/paper/2512.15468/) (2025)
- [Type-IV Code Clone Detection via Layer-Wise Non-Contrastive Representation Learning](https://mlsanity.com/paper/2609.17338/) (2026)

## Abstract (arXiv)

Software clone detection identifies similar code snippets. It has been an active research topic that attracts extensive attention over the last two decades. In recent years, machine learning (ML) based detectors, especially deep learning-based ones, have demonstrated impressive capability on clone detection. It seems that this longstanding problem has already been tamed owing to the advances in ML techniques. In this work, we would like to challenge the robustness of the recent ML-based clone detectors through code semantic-preserving transformations. We first utilize fifteen simple code transformation operators combined with commonly-used heuristics (i.e., Random Search, Genetic Algorithm, and Markov Chain Monte Carlo) to perform equivalent program transformation. Furthermore, we propose a deep reinforcement learning-based sequence generation (DRLSG) strategy to effectively guide the search process of generating clones that could escape from the detection. We then evaluate the ML-based detectors with the pairs of original and generated clones. We realize our method in a framework named CloneGen. CloneGen In evaluation, we challenge the two state-of-the-art ML-based detectors and four traditional detectors with the code clones after semantic-preserving transformations via the aid of CloneGen. Surprisingly, our experiments show that, despite the notable successes achieved by existing clone detectors, the ML models inside these detectors still cannot distinguish numerous clones produced by the code transformations in CloneGen. In addition, adversarial training of ML-based clone detectors using clones generated by CloneGen can improve their robustness and accuracy. CloneGen Meanwhile, compared with the commonly-used heuristics, the DRLSG strategy has shown the best effectiveness in generating code clones to decrease the detection accuracy of the ML-based detectors.