all InfoSec news
Exploring Backdoor Vulnerabilities of Chat Models
April 4, 2024, 4:10 a.m. | Yunzhuo Hao, Wenkai Yang, Yankai Lin
cs.CR updates on arXiv.org arxiv.org
Abstract: Recent researches have shown that Large Language Models (LLMs) are susceptible to a security threat known as Backdoor Attack. The backdoored model will behave well in normal cases but exhibit malicious behaviours on inputs inserted with a specific backdoor trigger. Current backdoor studies on LLMs predominantly focus on instruction-tuned LLMs, while neglecting another realistic scenario where LLMs are fine-tuned on multi-turn conversational data to be chat models. Chat models are extensively adopted across various real-world …
arxiv attack backdoor backdoor attack cases chat cs.ai cs.cl cs.cr current focus inputs language language models large llms malicious normal security security threat studies threat trigger vulnerabilities
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Azure DevSecOps Cloud Engineer II
@ Prudent Technology | McLean, VA, USA
Security Engineer III - Python, AWS
@ JPMorgan Chase & Co. | Bengaluru, Karnataka, India
SOC Analyst (Threat Hunter)
@ NCS | Singapore, Singapore
Managed Services Information Security Manager
@ NTT DATA | Sydney, Australia
Senior Security Engineer (Remote)
@ Mattermost | United Kingdom
Penetration Tester (Part Time & Remote)
@ TestPros | United States - Remote