mlsanityData to 14 Oct 2026

Impeding LLM-assisted Cheating in Introductory Programming Assignments via Adversarial Perturbation

arXiv 2410.09318 ↗First posted 12 Oct 2024cs.CL cs.CY cs.SEcited by 5

Not on the map. Why?

Abstract (arXiv)

While Large language model (LLM)-based programming assistants such as CoPilot and ChatGPT can help improve the productivity of professional software developers, they can also facilitate cheating in introductory computer programming courses. Assuming instructors have limited control over the industrial-strength models, this paper investigates the baseline performance of 5 widely used LLMs on a collection of introductory programming problems, examines adversarial perturbations to degrade their performance, and describes the results of a user study aimed at understanding the efficacy of such perturbations in hindering actual code generation for introductory programming assignments. The user study suggests that i) perturbations combinedly reduced the average correctness score by 77%, ii) the drop in correctness caused by these perturbations was affected based on their detectability.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 25 of its 61 references that are in the map. First posted on arXiv 12 Oct 2024.

Builds on

25 of 61 references.

References · 25

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  2. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  3. 2020Extracting Training Data from Large Language Modelscited by 2,189
  4. 2023Code Llama: Open Foundation Models for Codecited by 2,139
  5. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 841
  6. 2021Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigmcited by 606
  7. 2018Generating Natural Language Adversarial Examplescited by 424
  8. 2023Can AI-Generated Text be Reliably Detected?cited by 386
  9. 2019SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimizationcited by 254
  10. 2021Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Modelscited by 232
  11. 2023On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspectivecited by 211
  12. 2023Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attackscited by 194
13 more
  1. 2021Counterfactual Memorization in Neural Language Modelscited by 156
  2. 2021Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learnerscited by 115
  3. 2020Reevaluating Adversarial Examples in Natural Languagecited by 85
  4. 2023Large Language Models and Simple, Stupid Bugscited by 45
  5. 2017A4NT: Author Attribute Anonymity by Adversarial Training of Neural Machine Translationcited by 42
  6. 2020Adversarial Robustness for Codecited by 38
  7. 2023Detecting LLM-Generated Text in Computing Education: A Comparative Study for ChatGPT Casescited by 32
  8. 2022Character-level White-Box Adversarial Attacks against Transformers via Attachable Subwords Substitutioncited by 28
  9. 2017Foolbox: A Python toolbox to benchmark the robustness of machine learning modelscited by 20
  10. 2020Generating End-to-End Adversarial Examples for Malware Classifiers Using Explainabilitycited by 9
  11. 2021Trojan Source: Invisible Vulnerabilitiescited by 8
  12. 2021Mate! Are You Really Aware? An Explainability-Guided Testing Framework for Robustness of Malware Detectorscited by 7
  13. 2021R&R: Metric-guided Adversarial Sentence Generationcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026AICD Bench: A Challenging Benchmark for AI-Generated Code Detectioncited by 2
  2. 2026DoPE: Decoy Oriented Perturbation Encapsulation Human-Readable, AI-Hostile Documents for Academic Integritycited by 1
  3. 2026Off-The-Shelf Image-to-Image Models Are All You Need To Defeat Image Protection Schemescited by 1
  4. 2026Homoglyph-based Adversarial Perturbation of Introductory Computer Science Theory Problemscited by 0
  5. 2026Evaluating the Semantic-to-Geometric Gap in Adversarial Defenses Against Vision-Language Model-Based Plagiarismcited by 0