all InfoSec news
Prompt Stealing Attacks Against Large Language Models
Feb. 21, 2024, 5:11 a.m. | Zeyang Sha, Yang Zhang
cs.CR updates on arXiv.org arxiv.org
Abstract: The increasing reliance on large language models (LLMs) such as ChatGPT in various fields emphasizes the importance of ``prompt engineering,'' a technology to improve the quality of model outputs. With companies investing significantly in expert prompt engineers and educational resources rising to meet market demand, designing high-quality prompts has become an intriguing challenge. In this paper, we propose a novel attack against LLMs, named prompt stealing attacks. Our proposed prompt stealing attack aims to steal …
arxiv attacks chatgpt companies cs.cl cs.cr demand educational educational resources engineering engineers expert high investing language language models large llms market prompt prompts quality resources rising stealing technology
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Senior Security Officer
@ eSimplicity | Remote
Senior - Automated Cyber Attack Engineer
@ Deloitte | Madrid, España
Public Key Infrastructure (PKI) Senior Engineer
@ Sherwin-Williams | Cleveland, OH, United States
Consultant, Technology Consulting, Cyber Security - Privacy (Senior) (Multiple Positions) (1502793)
@ EY | Chicago, IL, US, 60606
Principal Associate, CSOC Analyst
@ Capital One | McLean, VA
Real Estate Portfolio & Corporate Security Lead
@ Lilium | Munich