Trojans in Large Language Models of Code: A Critical Review through a Trigger-Based Taxonomy

arXiv:2405.02828v1 Announce Type: cross
Abstract: Large language models (LLMs) have provided a lot of exciting new capabilities in software development. However, the opaque nature of these models makes them difficult to reason about and inspect. Their opacity gives rise to potential security risks, as adversaries can train and deploy compromised models to disrupt the software development process in the victims' organization.
This work presents an overview of the current state-of-the-art trojan attacks on large language models of code, with a …

abstract arxiv capabilities code cs.lg cs.se development however language language models large language large language models llms nature reason review risks security software software development taxonomy them through type