Constrained Decoding for Secure Code Generation

arXiv:2405.00218v1 Announce Type: new
Abstract: Code Large Language Models (Code LLMs) have been increasingly used by developers to boost productivity, but they often generate vulnerable code. Thus, there is an urgent need to ensure that code generated by Code LLMs is correct and secure. Previous research has primarily focused on generating secure code, overlooking the fact that secure code also needs to be correct. This oversight can lead to a false sense of security. Currently, the community lacks a method …

arxiv code cs.ai cs.cr cs.lg cs.se decoding developers generated language language models large llms productivity research secure code urgent vulnerable