all InfoSec news
Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learning
Feb. 27, 2024, 5:11 a.m. | Shuai Zhao, Meihuizi Jia, Luu Anh Tuan, Fengjun Pan, Jinming Wen
cs.CR updates on arXiv.org arxiv.org
Abstract: In-context learning, a paradigm bridging the gap between pre-training and fine-tuning, has demonstrated high efficacy in several NLP tasks, especially in few-shot settings. Despite being widely applied, in-context learning is vulnerable to malicious attacks. In this work, we raise security concerns regarding this paradigm. Our studies demonstrate that an attacker can manipulate the behavior of large language models by poisoning the demonstration context, without the need for fine-tuning the model. Specifically, we design a new …
arxiv attacks backdoor backdoor attacks bridging the gap context cs.ai cs.cl cs.cr fine-tuning gap high language language models large malicious nlp paradigm security security concerns settings training vulnerabilities vulnerable work
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Cyber Security Engineer I
@ Fortress Security Risk Management | Cleveland, OH, United States
Senior DevSecOps Engineer
@ Wisk Aero | Remote United States
Vulnerable Adult Investigator - Vice President
@ JPMorgan Chase & Co. | Chicago, IL, United States
Consultant Réseaux IT Digital Impulse - H/F
@ Talan | Paris, France
DevSecOps Engineer (Onsite)
@ Accenture Federal Services | Arlington, VA
Senior Security Engineer
@ Minitab | State College, Pennsylvania, United States