all InfoSec news
TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification
Feb. 21, 2024, 5:11 a.m. | Martin Gubri, Dennis Ulmer, Hwaran Lee, Sangdoo Yun, Seong Joon Oh
cs.CR updates on arXiv.org arxiv.org
Abstract: Large Language Model (LLM) services and models often come with legal rules on who can use them and how they must use them. Assessing the compliance of the released LLMs is crucial, as these rules protect the interests of the LLM contributor and prevent misuse. In this context, we describe the novel problem of Black-box Identity Verification (BBIV). The goal is to determine whether a third-party application uses a certain LLM through its chat function. …
adversarial arxiv box can compliance cs.ai cs.cl cs.cr cs.lg honeypot identification language large large language model legal llm llms prompt protect random rules services
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Information Security Engineers
@ D. E. Shaw Research | New York City
Technology Security Analyst
@ Halton Region | Oakville, Ontario, Canada
Senior Cyber Security Analyst
@ Valley Water | San Jose, CA
Cyber Crime Student Internship
@ West Midlands Police | Birmingham, West Midlands, United Kingdom
Cyber Security Engineer (Junior/Journeyman)
@ CSEngineering | El Segundo, CA 90245, USA
Application Security Lead
@ Tokio Marine HCC | United Kingdom