all AI news
PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails
Feb. 27, 2024, 5:50 a.m. | Neal Mangaokar, Ashish Hooda, Jihye Choi, Shreyas Chandrashekaran, Kassem Fawaz, Somesh Jha, Atul Prakash
cs.CL updates on arXiv.org arxiv.org
Abstract: Large language models (LLMs) are typically aligned to be harmless to humans. Unfortunately, recent work has shown that such models are susceptible to automated jailbreak attacks that induce them to generate harmful content. More recent LLMs often incorporate an additional layer of defense, a Guard Model, which is a second LLM that is designed to check and moderate the output response of the primary LLM. Our key contribution is to show a novel attack strategy, …
abstract arxiv attacks automated cs.cl cs.cr defense generate humans jailbreak language language model language models large language large language model large language models layer llms rails them type universal work
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
#13721 - Data Engineer - AI Model Testing
@ Qualitest | Miami, Florida, United States
Elasticsearch Administrator
@ ManTech | 201BF - Customer Site, Chantilly, VA