mlsanityData to 14 Oct 2026

Adversarial Robustness for Code

arXiv 2002.04694 ↗First posted 11 Feb 2020cs.LG cs.PL cs.SEcited by 38

Not on the map. Why?

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.

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

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 6; 2022: 9; 2023: 7; 2024: 7; 2025: 5; 2026: 4.

38 papers.

Sort:

By area:

  1. 2022ReCode: Robustness Evaluation of Code Generation Modelscited by 103
  2. 2023Transformers Meet Directed Graphscited by 40
  3. 2021Scalable Certified Segmentation via Randomized Smoothingcited by 35
  4. 2023Uncovering the Limits of Machine Learning for Automatic Vulnerability Detectioncited by 30
  5. 2024Astraios: Parameter-Efficient Instruction Tuning Code Large Language Modelscited by 23
  6. 2021Generating Adversarial Computer Programs using Optimized Obfuscationscited by 22
  7. 2021Understanding Neural Code Intelligence Through Program Simplificationcited by 22
  8. 2023Deep Learning for Code Intelligence: Survey, Benchmark and Toolkitcited by 22
  9. 2021Memorization and Generalization in Neural Code Intelligence Modelscited by 19
  10. 2022RoPGen: Towards Robust Code Authorship Attribution via Automatic Coding Style Transformationcited by 15
  11. 2022On Distribution Shift in Learning-based Bug Detectorscited by 15
  12. 2023Do Large Language Models Pay Similar Attention Like Human Programmers When Generating Code?cited by 14
26 more
  1. 2023From Robustness to Explainability and Back Againcited by 14
  2. 2022HierarchyNet: Learning to Summarize Source Code with Heterogeneous Representationscited by 9
  3. 2023Boosting Source Code Learning with Text-Oriented Data Augmentation: An Empirical Studycited by 5
  4. 2024Impeding LLM-assisted Cheating in Introductory Programming Assignments via Adversarial Perturbationcited by 5
  5. 2021Towards Making Deep Learning-based Vulnerability Detectors Robustcited by 4
  6. 2022MIXCODE: Enhancing Code Classification by Mixup-Based Data Augmentationcited by 4
  7. 2024CodeFort: Robust Training for Code Generation Modelscited by 4
  8. 2024Measuring Impacts of Poisoning on Model Parameters and Embeddings for Large Language Models of Codecited by 4
  9. 2024Does Self-Attention Need Separate Weights in Transformers?cited by 4
  10. 2025XOXO: Stealthy Cross-Origin Context Poisoning Attacks against AI Coding Assistantscited by 4
  11. 2025The Hitchhiker's Guide to Program Analysis, Part II: Deep Thoughts by LLMscited by 4
  12. 2025EditLord: Learning Code Transformation Rules for Code Editingcited by 4
  13. 2022Characterizing and Understanding the Behavior of Quantized Models for Reliable Deploymentcited by 2
  14. 2022Semantic-Preserving Adversarial Code Comprehensioncited by 2
  15. 2022CLAWSAT: Towards Both Robust and Accurate Code Modelscited by 2
  16. 2023Transfer Attacks and Defenses for Large Language Models on Coding Taskscited by 2
  17. 2024GenCode: A Generic Data Augmentation Framework for Boosting Deep Learning-Based Code Understandingcited by 2
  18. 2025Semantic-Preserving Transformations as Mutation Operators: A Study on Their Effectiveness in Defect Detectioncited by 2
  19. 2026A Jagged Frontier: Evaluating Robustness of Code Agents to Semantics-Preserving Transformationscited by 2
  20. 2021Energy-bounded Learning for Robust Models of Codecited by 1
  21. 2022Unveiling Project-Specific Bias in Neural Code Modelscited by 1
  22. 2024Measuring Impacts of Poisoning on Model Parameters and Neuron Activations: A Case Study of Poisoning CodeBERTcited by 1
  23. 2025Cross-site scripting adversarial attacks based on deep reinforcement learning: Evaluation and extension studycited by 0
  24. 2026Learning Generalizable Multimodal Representations for Software Vulnerability Detectioncited by 0
  25. 2026Invariant Pretraining for Robust Code Representationscited by 0
  26. 2026On the Lexical Superstition of Large Language Models for Code Comprehension: Re-evaluation on Code of Low Lexical Qualitycited by 0