mlsanityData to 7 Oct 2026

Do Users Write More Insecure Code with AI Assistants?

arXiv 2211.03622 ↗First posted 7 Nov 2022cs.CRcited by 186

Not on the map. Why?

Cited by 35 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We conduct the first large-scale user study examining how users interact with an AI Code assistant to solve a variety of security related tasks across different programming languages. Overall, we find that participants who had access to an AI assistant based on OpenAI's codex-davinci-002 model wrote significantly less secure code than those without access. Additionally, participants with access to an AI assistant were more likely to believe they wrote secure code than those without access to the AI assistant. Furthermore, we find that participants who trusted the AI less and engaged more with the language and format of their prompts (e.g. re-phrasing, adjusting temperature) provided code with fewer security vulnerabilities. Finally, in order to better inform the design of future AI-based Code assistants, we provide an in-depth analysis of participants' language and interaction behavior, as well as release our user interface as an instrument to conduct similar studies in the future.

Key facts. Cited by 186 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Nov 2022.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 19; 2024: 43; 2025: 56; 2026: 67.

186 papers.

Sort:

By area:

  1. 2023Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedbackcited by 743
  2. 2025Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMscited by 158
  3. 2024LLM Critics Help Catch LLM Bugscited by 138
  4. 2024Language Models Learn to Mislead Humans via RLHFcited by 118
  5. 2023Learning Performance-Improving Code Editscited by 103
  6. 2024Formal Mathematical Reasoning: A New Frontier in AIcited by 80
  7. 2023Overthinking the Truth: Understanding how Language Models Process False Demonstrationscited by 78
  8. 2023Can ChatGPT replace StackOverflow? A Study on Robustness and Reliability of Large Language Model Code Generationcited by 72
  9. 2024Large Language Models for Cyber Security: A Systematic Literature Reviewcited by 65
  10. 2022Parsel: Algorithmic Reasoning with Language Models by Composing Decompositionscited by 62
  11. 2023Clover: Closed-Loop Verifiable Code Generationcited by 62
  12. 2024We Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMscited by 61
38 more
  1. 2023Computing Education in the Era of Generative AIcited by 50
  2. 2024A Performance Study of LLM-Generated Code on Leetcodecited by 48
  3. 2023TrojanPuzzle: Covertly Poisoning Code-Suggestion Modelscited by 47
  4. 2023Large Language Models and Simple, Stupid Bugscited by 45
  5. 2023RepoFusion: Training Code Models to Understand Your Repositorycited by 40
  6. 2023Thrilled by Your Progress! Large Language Models (GPT-4) No Longer Struggle to Pass Assessments in Higher Education Programming Coursescited by 38
  7. 2026SWE-chat: Coding Agent Interactions From Real Users in the Wildcited by 36
  8. 2023SALLM: Security Assessment of Generated Codecited by 35
  9. 2024Constrained Decoding for Secure Code Generationcited by 35
  10. 2024Automatic Programming: Large Language Models and Beyondcited by 35
  11. 2024Prompting Techniques for Secure Code Generation: A Systematic Investigationcited by 33
  12. 2024AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinementcited by 33
  13. 2026Dive into Claude Code: The Design Space of Today's and Future AI Agent Systemscited by 33
  14. 2023The FormAI Dataset: Generative AI in Software Security Through the Lens of Formal Verificationcited by 32
  15. 2026Agentic Much? Adoption of Coding Agents on GitHubcited by 31
  16. 2023Democratising AI: Multiple Meanings, Goals, and Methodscited by 29
  17. 2023The Shaky Foundations of Clinical Foundation Models: A Survey of Large Language Models and Foundation Models for EMRscited by 29
  18. 2024The RealHumanEval: Evaluating Large Language Models' Abilities to Support Programmerscited by 28
  19. 2024Toward Secure Code Generation: Bridging Correctness and Security via Task-Adaptive Vulnerability Modeling and Execution-Based Benchmarkingcited by 26
  20. 2024Do Large Language Models Perform the Way People Expect? Measuring the Human Generalization Functioncited by 24
  21. 2025The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMscited by 24
  22. 2024NoFunEval: Funny How Code LMs Falter on Requirements Beyond Functional Correctnesscited by 23
  23. 2024Learning Agent-based Modeling with LLM Companions: Experiences of Novices and Experts Using ChatGPT & NetLogo Chatcited by 23
  24. 2024How secure is AI-generated Code: A Large-Scale Comparison of Large Language Modelscited by 23
  25. 2025Speed at the Cost of Quality: How Cursor AI Increases Short-Term Velocity and Long-Term Complexity in Open-Source Projectscited by 23
  26. 2024PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedbackcited by 22
  27. 2024LLMs in Web Development: Evaluating LLM-Generated PHP Code Unveiling Vulnerabilities and Limitationscited by 21
  28. 2024Generative Monoculture in Large Language Modelscited by 21
  29. 2023Generation Probabilities Are Not Enough: Uncertainty Highlighting in AI Code Completionscited by 20
  30. 2023The Intended Uses of Automated Fact-Checking Artefacts: Why, How and Whocited by 19
  31. 2025Security and Quality in LLM-Generated Code: A Multi-Language, Multi-Model Analysiscited by 18
  32. 2024PromSec: Prompt Optimization for Secure Generation of Functional Source Code with Large Language Models (LLMs)cited by 17
  33. 2025Correctness Assessment of Code Generated by Large Language Models Using Internal Representationscited by 17
  34. 2023Enhancing Large Language Models for Secure Code Generation: A Dataset-driven Study on Vulnerability Mitigationcited by 14
  35. 2025CodeIF-Bench: Evaluating Instruction-Following Capabilities of Large Language Models in Interactive Code Generationcited by 14
  36. 2025"Your AI, My Shell": Demystifying Prompt Injection Attacks on Agentic AI Coding Editorscited by 14
  37. 2024Rocks Coding, Not Development--A Human-Centric, Experimental Evaluation of LLM-Supported SE Taskscited by 13
  38. 2024LiCoEval: Evaluating LLMs on License Compliance in Code Generationcited by 13

50 most cited of 186 All 186 (JSON)