all AI news
Defending Against Indirect Prompt Injection Attacks With Spotlighting
March 25, 2024, 4:41 a.m. | Keegan Hines, Gary Lopez, Matthew Hall, Federico Zarfati, Yonatan Zunger, Emre Kiciman
cs.LG updates on arXiv.org arxiv.org
Abstract: Large Language Models (LLMs), while powerful, are built and trained to process a single text input. In common applications, multiple inputs can be processed by concatenating them together into a single stream of text. However, the LLM is unable to distinguish which sections of prompt belong to various input sources. Indirect prompt injection attacks take advantage of this vulnerability by embedding adversarial instructions into untrusted data being processed alongside user commands. Often, the LLM will …
abstract applications arxiv attacks cs.cl cs.cr cs.lg however inputs language language models large language large language models llm llms multiple process prompt prompt injection prompt injection attacks text them together type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Senior Data Engineer
@ Quantexa | Sydney, New South Wales, Australia
Staff Analytics Engineer
@ Warner Bros. Discovery | NY New York 230 Park Avenue South