LLMs in Web Development: Evaluating LLM-Generated PHP Code Unveiling Vulnerabilities and Limitations
Authors:
- Rebeka TóthRTRebeka Tóth
- Tamas BisztrayTBTamas Bisztray
- ErdődiERErdődi
- LászlóLÁLászló
- László ErdődiLELászló Erdődi
- 9 September 2024
- book chapter
- Published by Springer Nature
- p. 425-437
Abstract
No abstract availableKeywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Self-Collaboration Code Generation via ChatGPTACM Transactions on Software Engineering and Methodology, 2024
- Learning Defect Prediction from Unrealistic Data2024
- The FormAI Dataset: Generative AI in Software Security through the Lens of Formal Verification2023
- Do Users Write More Insecure Code with AI Assistants?2023
- DiverseVul: A New Vulnerable Source Code Dataset for Deep Learning Based Vulnerability Detection2023
- The Programmer’s Assistant: Conversational Interaction with a Large Language Model for Software Development2023
- Deriving Modernity Signatures for PHP Systems with Static Analysis2022
- Less is Often More: Header Whitelisting as Semantic Gap Mitigation in HTTP-Based Software Systems2021
- Evolution of method invocation and object instantiation patterns in a PHP ecosystem2016
- Software verification and validation: an overviewIEEE Software, 1989