# Adversarial Robustness for Code

arXiv: https://arxiv.org/abs/2002.04694 · HTML: https://mlsanity.com/paper/2002.04694/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Feb 2020.

## Built on by (most cited first, 30 of 38)

- [ReCode: Robustness Evaluation of Code Generation Models](https://mlsanity.com/paper/2212.10264/) (2022)
- [Transformers Meet Directed Graphs](https://mlsanity.com/paper/2302.00049/) (2023)
- [Scalable Certified Segmentation via Randomized Smoothing](https://mlsanity.com/paper/2107.00228/) (2021)
- [Uncovering the Limits of Machine Learning for Automatic Vulnerability Detection](https://mlsanity.com/paper/2306.17193/) (2023)
- [Astraios: Parameter-Efficient Instruction Tuning Code Large Language Models](https://mlsanity.com/paper/2401.00788/) (2024)
- [Generating Adversarial Computer Programs using Optimized Obfuscations](https://mlsanity.com/paper/2103.11882/) (2021)
- [Understanding Neural Code Intelligence Through Program Simplification](https://mlsanity.com/paper/2106.03353/) (2021)
- [Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit](https://mlsanity.com/paper/2401.00288/) (2023)
- [Memorization and Generalization in Neural Code Intelligence Models](https://mlsanity.com/paper/2106.08704/) (2021)
- [RoPGen: Towards Robust Code Authorship Attribution via Automatic Coding Style Transformation](https://mlsanity.com/paper/2202.06043/) (2022)
- [On Distribution Shift in Learning-based Bug Detectors](https://mlsanity.com/paper/2204.10049/) (2022)
- [Do Large Language Models Pay Similar Attention Like Human Programmers When Generating Code?](https://mlsanity.com/paper/2306.01220/) (2023)
- [From Robustness to Explainability and Back Again](https://mlsanity.com/paper/2306.03048/) (2023)
- [HierarchyNet: Learning to Summarize Source Code with Heterogeneous Representations](https://mlsanity.com/paper/2205.15479/) (2022)
- [Boosting Source Code Learning with Text-Oriented Data Augmentation: An Empirical Study](https://mlsanity.com/paper/2303.06808/) (2023)
- [Impeding LLM-assisted Cheating in Introductory Programming Assignments via Adversarial Perturbation](https://mlsanity.com/paper/2410.09318/) (2024)
- [Towards Making Deep Learning-based Vulnerability Detectors Robust](https://mlsanity.com/paper/2108.00669/) (2021)
- [MIXCODE: Enhancing Code Classification by Mixup-Based Data Augmentation](https://mlsanity.com/paper/2210.03003/) (2022)
- [CodeFort: Robust Training for Code Generation Models](https://mlsanity.com/paper/2405.01567/) (2024)
- [Measuring Impacts of Poisoning on Model Parameters and Embeddings for Large Language Models of Code](https://mlsanity.com/paper/2405.11466/) (2024)
- [Does Self-Attention Need Separate Weights in Transformers?](https://mlsanity.com/paper/2412.00359/) (2024)
- [XOXO: Stealthy Cross-Origin Context Poisoning Attacks against AI Coding Assistants](https://mlsanity.com/paper/2503.14281/) (2025)
- [The Hitchhiker's Guide to Program Analysis, Part II: Deep Thoughts by LLMs](https://mlsanity.com/paper/2504.11711/) (2025)
- [EditLord: Learning Code Transformation Rules for Code Editing](https://mlsanity.com/paper/2504.15284/) (2025)
- [Characterizing and Understanding the Behavior of Quantized Models for Reliable Deployment](https://mlsanity.com/paper/2204.04220/) (2022)
- [Semantic-Preserving Adversarial Code Comprehension](https://mlsanity.com/paper/2209.05130/) (2022)
- [CLAWSAT: Towards Both Robust and Accurate Code Models](https://mlsanity.com/paper/2211.11711/) (2022)
- [Transfer Attacks and Defenses for Large Language Models on Coding Tasks](https://mlsanity.com/paper/2311.13445/) (2023)
- [GenCode: A Generic Data Augmentation Framework for Boosting Deep Learning-Based Code Understanding](https://mlsanity.com/paper/2402.15769/) (2024)
- [Semantic-Preserving Transformations as Mutation Operators: A Study on Their Effectiveness in Defect Detection](https://mlsanity.com/paper/2503.23448/) (2025)

## Abstract (arXiv)

Machine learning and deep learning in particular has been recently used to successfully address many tasks in the domain of code such as finding and fixing bugs, code completion, decompilation, type inference and many others. However, the issue of adversarial robustness of models for code has gone largely unnoticed. In this work, we explore this issue by: (i) instantiating adversarial attacks for code (a domain with discrete and highly structured inputs), (ii) showing that, similar to other domains, neural models for code are vulnerable to adversarial attacks, and (iii) combining existing and novel techniques to improve robustness while preserving high accuracy.