all AI news
CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models
Feb. 27, 2024, 5:50 a.m. | Huijie Lv, Xiao Wang, Yuansen Zhang, Caishuang Huang, Shihan Dou, Junjie Ye, Tao Gui, Qi Zhang, Xuanjing Huang
cs.CL updates on arXiv.org arxiv.org
Abstract: Adversarial misuse, particularly through `jailbreaking' that circumvents a model's safety and ethical protocols, poses a significant challenge for Large Language Models (LLMs). This paper delves into the mechanisms behind such successful attacks, introducing a hypothesis for the safety mechanism of aligned LLMs: intent security recognition followed by response generation. Grounded in this hypothesis, we propose CodeChameleon, a novel jailbreak framework based on personalized encryption tactics. To elude the intent security recognition phase, we reformulate tasks …
abstract adversarial arxiv attacks challenge cs.ai cs.cl cs.cr encryption ethical framework hypothesis jailbreaking language language models large language large language models llms misuse paper personalized recognition safety security through type
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
Senior ML Engineer
@ Carousell Group | Ho Chi Minh City, Vietnam
Data and Insight Analyst
@ Cotiviti | Remote, United States