all InfoSec news
StructuralSleight: Automated Jailbreak Attacks on Large Language Models Utilizing Uncommon Text-Encoded Structure
June 14, 2024, 4:19 a.m. | Bangxin Li, Hengrui Xing, Chao Huang, Jin Qian, Huangqing Xiao, Linfeng Feng, Cong Tian
cs.CR updates on arXiv.org arxiv.org
Abstract: Large Language Models (LLMs) are widely used in natural language processing but face the risk of jailbreak attacks that maliciously induce them to generate harmful content. Existing jailbreak attacks, including character-level and context-level attacks, mainly focus on the prompt of the plain text without specifically exploring the significant influence of its structure. In this paper, we focus on studying how prompt structure contributes to the jailbreak attack. We introduce a novel structure-level attack method based …
arxiv attacks automated context cs.cl cs.cr focus jailbreak language language models large llms natural natural language natural language processing plain text prompt risk structure text uncommon
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Information Technology Specialist I: Windows Engineer
@ Los Angeles County Employees Retirement Association (LACERA) | Pasadena, California
Information Technology Specialist I, LACERA: Information Security Engineer
@ Los Angeles County Employees Retirement Association (LACERA) | Pasadena, CA
Solutions Expert
@ General Dynamics Information Technology | USA MD Home Office (MDHOME)
Physical Security Specialist
@ The Aerospace Corporation | Chantilly
System Administrator
@ General Dynamics Information Technology | USA VA Newington - Customer Proprietary (VAC395)
Microsoft Exchange & 365 Systems Engineer - TS/SCI with Polygraph
@ General Dynamics Information Technology | USA VA Chantilly - 14700 Lee Rd (VAS100)