all AI news
Neural Exec: Learning (and Learning from) Execution Triggers for Prompt Injection Attacks
March 7, 2024, 5:42 a.m. | Dario Pasquini, Martin Strohmeier, Carmela Troncoso
cs.LG updates on arXiv.org arxiv.org
Abstract: We introduce a new family of prompt injection attacks, termed Neural Exec. Unlike known attacks that rely on handcrafted strings (e.g., "Ignore previous instructions and..."), we show that it is possible to conceptualize the creation of execution triggers as a differentiable search problem and use learning-based methods to autonomously generate them.
Our results demonstrate that a motivated adversary can forge triggers that are not only drastically more effective than current handcrafted ones but also exhibit …
abstract arxiv attacks cs.cr cs.lg differentiable exec family prompt prompt injection prompt injection attacks search show strings 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