Open Access
- 18 June 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 600-603
Abstract
Many developers rely on Large Language Models (LLMs) to facilitate software development. Nevertheless, these models have exhibited limited capabilities in the security domain. We introduce LLMSecGuard, a framework to offer enhanced code security through the synergy between static code analyzers and LLMs. LLMSecGuard is open source and aims to equip developers with code solutions that are more secure than the code initially generated by LLMs. This framework also has a benchmarking feature, aimed at providing insights into the evolving security attributes of these models.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- Is GitHub’s Copilot as bad as humans at introducing vulnerabilities in code?Empirical Software Engineering, 2023
- Asleep at the Keyboard? Assessing the Security of GitHub Copilot’s Code Contributions2022
- Evaluation of Static Vulnerability Detection Tools With Java Cryptographic API BenchmarksIEEE Transactions on Software Engineering, 2022
- Worrisome Patterns in Developers: A Survey in Cryptography2021
- Security Smells Pervade Mobile App Servers2021
- Java Cryptography Uses in the Wild2020
- Security code smells in Android ICCEmpirical Software Engineering, 2018
- Idea: Benchmarking Android Data Leak Detection Tools2018
- JIT feedback2018
- Security Smells in Android2017