mlsanityData to 7 Oct 2026

Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions

arXiv 2108.09293 ↗First posted 20 Aug 2021cs.CR cs.AIcited by 417

Not on the map. Why?

Cited by 82 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

There is burgeoning interest in designing AI-based systems to assist humans in designing computing systems, including tools that automatically generate computer code. The most notable of these comes in the form of the first self-described `AI pair programmer', GitHub Copilot, a language model trained over open-source GitHub code. However, code often contains bugs - and so, given the vast quantity of unvetted code that Copilot has processed, it is certain that the language model will have learned from exploitable, buggy code. This raises concerns on the security of Copilot's code contributions. In this work, we systematically investigate the prevalence and conditions that can cause GitHub Copilot to recommend insecure code. To perform this analysis we prompt Copilot to generate code in scenarios relevant to high-risk CWEs (e.g. those from MITRE's "Top 25" list). We explore Copilot's performance on three distinct code generation axes -- examining how it performs given diversity of weaknesses, diversity of prompts, and diversity of domains. In total, we produce 89 different scenarios for Copilot to complete, producing 1,689 programs. Of these, we found approximately 40% to be vulnerable.

Key facts. Cited by 417 papers in the map (data through 7 Oct 2026). Builds on 10 of its 39 references that are in the map. First posted on arXiv 20 Aug 2021.

Builds on

10 of 39 references.

References · 10

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  5. 2021Program Synthesis with Large Language Modelscited by 3,509
  6. 2018CoQA: A Conversational Question Answering Challengecited by 674
  7. 2016Recurrent Neural Network for Text Classification with Multi-Task Learningcited by 144
  8. 2021CURE: Code-Aware Neural Machine Translation for Automatic Program Repaircited by 85
  9. 2020DAVE: Deriving Automatically Verilog from Englishcited by 46
  10. 2019Machine Translation from Natural Language to Code using Long-Short Term Memorycited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 11; 2023: 59; 2024: 88; 2025: 112; 2026: 147.

417 papers.

Sort:

By area:

  1. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 1,906
  2. 2022Discovering Language Model Behaviors with Model-Written Evaluationscited by 805
  3. 2023StarCoder: may the source be with you!cited by 790
  4. 2023A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPTcited by 612
  5. 2023VeriGen: A Large Language Model for Verilog Code Generationcited by 197
  6. 2022GitHub Copilot AI pair programmer: Asset or Liability?cited by 150
  7. 2023Large Language Models for Code: Security Hardening and Adversarial Testingcited by 149
  8. 2023Chip-Chat: Challenges and Opportunities in Conversational Hardware Designcited by 136
  9. 2022Large Language Models Meet NL2Code: A Surveycited by 135
  10. 2023Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Modelscited by 130
  11. 2023Who Wrote this Code? Watermarking for Code Generationcited by 116
  12. 2022Benchmarking Large Language Models for Automated Verilog RTL Code Generationcited by 112
38 more
  1. 2022Programming Is Hard -- Or at Least It Used to Be: Educational Opportunities And Challenges of AI Code Generationcited by 97
  2. 2022Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programmingcited by 91
  3. 2023Identifying and Mitigating the Security Risks of Generative AIcited by 90
  4. 2024NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Securitycited by 90
  5. 2022Execution-Based Evaluation for Open-Domain Code Generationcited by 89
  6. 2024RedCode: Risky Code Execution and Generation Benchmark for Code Agentscited by 87
  7. 2024Formal Mathematical Reasoning: A New Frontier in AIcited by 80
  8. 2024A New Era in LLM Security: Exploring Security Concerns in Real-World LLM-based Systemscited by 74
  9. 2023Can ChatGPT replace StackOverflow? A Study on Robustness and Reliability of Large Language Model Code Generationcited by 72
  10. 2024SpecRover: Code Intent Extraction via LLMscited by 71
  11. 2024When LLMs Meet Cybersecurity: A Systematic Literature Reviewcited by 70
  12. 2022Using Large Language Models to Enhance Programming Error Messagescited by 67
  13. 2023ChatGPT Prompt Patterns for Improving Code Quality, Refactoring, Requirements Elicitation, and Software Designcited by 66
  14. 2024Instruction Tuning for Secure Code Generationcited by 63
  15. 2023"It's Weird That it Knows What I Want": Usability and Interactions with Copilot for Novice Programmerscited by 62
  16. 2023Clover: Closed-Loop Verifiable Code Generationcited by 62
  17. 2024We Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMscited by 61
  18. 2023LLMSecEval: A Dataset of Natural Language Prompts for Security Evaluationscited by 58
  19. 2025CWEval: Outcome-driven Evaluation on Functionality and Security of LLM Code Generationcited by 55
  20. 2025A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasurescited by 54
  21. 2023Using Large Language Models to Generate JUnit Tests: An Empirical Studycited by 53
  22. 2023CodeLMSec Benchmark: Systematically Evaluating and Finding Security Vulnerabilities in Black-Box Code Language Modelscited by 52
  23. 2024Raidar: geneRative AI Detection viA Rewritingcited by 51
  24. 2023Computing Education in the Era of Generative AIcited by 50
  25. 2024WIPI: A New Web Threat for LLM-Driven Web Agentscited by 50
  26. 2024BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Modelscited by 50
  27. 2024A Performance Study of LLM-Generated Code on Leetcodecited by 48
  28. 2023TrojanPuzzle: Covertly Poisoning Code-Suggestion Modelscited by 47
  29. 2023Large Language Models and Simple, Stupid Bugscited by 45
  30. 2024Using AI-Based Coding Assistants in Practice: State of Affairs, Perceptions, and Ways Forwardcited by 44
  31. 2022What is it like to program with artificial intelligence?cited by 39
  32. 2025BaxBench: Can LLMs Generate Correct and Secure Backends?cited by 38
  33. 2024Securing Large Language Models: Threats, Vulnerabilities and Responsible Practicescited by 36
  34. 2026SWE-chat: Coding Agent Interactions From Real Users in the Wildcited by 36
  35. 2023In ChatGPT We Trust? Measuring and Characterizing the Reliability of ChatGPTcited by 35
  36. 2023SALLM: Security Assessment of Generated Codecited by 35
  37. 2024Constrained Decoding for Secure Code Generationcited by 35
  38. 2024Automatic Programming: Large Language Models and Beyondcited by 35

50 most cited of 417 All 417 (JSON)