Ocassionally Secure: A Comparative Analysis of Code Generation Assistants

• Published in: arXiv.org
• Main Authors: Elgedawy, Ran, Sadik, John, Dutta, Senjuti, Gautam, Anuj, Georgiou, Konstantinos, Gholamrezae, Farzin, Ji, Fujiao, Lim, Kyungchan, Liu, Qian, Ruoti, Scott
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 01.02.2024
• Subjects: Comparative analysis; Large language models; Security

\( \)Large Language Models (LLMs) are being increasingly utilized in various applications, with code generations being a notable example. While previous research has shown that LLMs have the capability to generate both secure and insecure code, the literature does not take into account what factors...