Adversarial Attacks and Defense for Conversation Entailment Task

arXiv:2405.00289v1 Announce Type: new
Abstract: Large language models (LLMs) that are proved to be very powerful on different NLP tasks. However, there are still many ways to attack the model with very low costs. How to defend the model becomes an important problem. In our work, we treat adversarial attack results as a new (unseen) domain of the model, and we frame the defending problem into how to improve the robustness of the model on the new domain. We focus …

abstract adversarial adversarial attacks arxiv attacks conversation costs cs.ai cs.cl defense however language language models large language large language models llms low nlp results tasks type work