Security weaknesses of copilot generated code in github

Y Fu, P Liang, A Tahir, Z Li, M Shahin, J Yu - arXiv preprint arXiv …, 2023 - arxiv.org
Modern code generation tools use AI models, particularly Large Language Models (LLMs),
to generate functional and complete code. While such tools are becoming popular and …

Asleep at the keyboard? assessing the security of github copilot's code contributions

H Pearce, B Ahmad, B Tan… - … IEEE Symposium on …, 2022 - ieeexplore.ieee.org
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 …

Just another copy and paste? Comparing the security vulnerabilities of ChatGPT generated code and StackOverflow answers

S Hamer, M d'Amorim, L Williams - 2024 IEEE Security and …, 2024 - ieeexplore.ieee.org
Sonatype's 2023 report found that 97% of developers and security leads integrate
generative Artificial Intelligence (AI), particularly Large Language Models (LLMs), into their …

Llmseceval: A dataset of natural language prompts for security evaluations

C Tony, M Mutas, NED Ferreyra… - 2023 IEEE/ACM 20th …, 2023 - ieeexplore.ieee.org
Large Language Models (LLMs) like Codex are powerful tools for performing code
completion and code generation tasks as they are trained on billions of lines of code from …

Generate and pray: Using sallms to evaluate the security of llm generated code

ML Siddiq, J Santos - arXiv preprint arXiv:2311.00889, 2023 - arxiv.org
With the growing popularity of Large Language Models (eg GitHub Copilot, ChatGPT, etc.) in
software engineers' daily practices, it is important to ensure that the code generated by these …

No need to lift a finger anymore? assessing the quality of code generation by chatgpt

Z Liu, Y Tang, X Luo, Y Zhou… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Large language models (LLMs) have demonstrated impressive capabilities across various
natural language processing (NLP) tasks, such as machine translation, question answering …

SecurityEval dataset: mining vulnerability examples to evaluate machine learning-based code generation techniques

ML Siddiq, JCS Santos - Proceedings of the 1st International Workshop …, 2022 - dl.acm.org
Automated source code generation is currently a popular machine-learning-based task. It
can be helpful for software developers to write functionally correct code from a given context …

{CodexLeaks}: Privacy leaks from code generation language models in {GitHub} copilot

L Niu, S Mirza, Z Maradni, C Pöpper - 32nd USENIX Security Symposium …, 2023 - usenix.org
Code generation language models are trained on billions of lines of source code to provide
code generation and auto-completion features, like those offered by code assistant GitHub …

Is github's copilot as bad as humans at introducing vulnerabilities in code?

O Asare, M Nagappan, N Asokan - Empirical Software Engineering, 2023 - Springer
Several advances in deep learning have been successfully applied to the software
development process. Of recent interest is the use of neural language models to build tools …

A lightweight framework for high-quality code generation

ML Siddiq, B Casey, J Santos - arXiv preprint arXiv:2307.08220, 2023 - arxiv.org
In recent years, the use of automated source code generation utilizing transformer-based
generative models has expanded, and these models can generate functional code …