CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models

arXiv:2406.12257v1 Announce Type: cross
Abstract: The remarkable performance of large language models (LLMs) in generation tasks has enabled practitioners to leverage publicly available models to power custom applications, such as chatbots and virtual assistants. However, the data used to train or fine-tune these LLMs is often undisclosed, allowing an attacker to compromise the data and inject backdoors into the models. In this paper, we develop a novel inference time defense, named CleanGen, to mitigate backdoor attacks for generation tasks in …

applications arxiv attacks backdoor backdoor attacks chatbots cs.ai cs.cr custom custom applications data language language models large llms performance power remarkable train virtual