all InfoSec news
SPML: A DSL for Defending Language Models Against Prompt Attacks
Feb. 20, 2024, 5:11 a.m. | Reshabh K Sharma, Vinayak Gupta, Dan Grossman
cs.CR updates on arXiv.org arxiv.org
Abstract: Large language models (LLMs) have profoundly transformed natural language applications, with a growing reliance on instruction-based definitions for designing chatbots. However, post-deployment the chatbot definitions are fixed and are vulnerable to attacks by malicious users, emphasizing the need to prevent unethical applications and financial losses. Existing studies explore user prompts' impact on LLM-based chatbots, yet practical methods to contain attacks on application-specific chatbots remain unexplored. This paper presents System Prompt Meta Language (SPML), a domain-specific …
arxiv attacks cs.cl cs.cr cs.lg cs.pl defending dsl language language models prompt
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Sr. Staff Security Engineer
@ Databricks | San Francisco, California
Security Engineer
@ Nomi Health | Austin, Texas
Senior Principal Consultant, Security Architecture
@ 6point6 | Manchester, United Kingdom
Cyber Policy Advisor
@ IntelliBridge | McLean, VA, McLean, VA, US
TW Full Stack Software Engineer (Access Control & Intrusion Systems)
@ Bosch Group | Taipei, Taiwan
Cyber Software Engineer
@ Peraton | Annapolis Junction, MD, United States