all InfoSec news
Neural Exec: Learning (and Learning from) Execution Triggers for Prompt Injection Attacks
March 7, 2024, 5:11 a.m. | Dario Pasquini, Martin Strohmeier, Carmela Troncoso
cs.CR 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 …
arxiv attacks cs.cr cs.lg family injection injection attacks problem prompt prompt injection prompt injection attacks search strings
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
CyberSOC Technical Lead
@ Integrity360 | Sandyford, Dublin, Ireland
Cyber Security Strategy Consultant
@ Capco | New York City
Cyber Security Senior Consultant
@ Capco | Chicago, IL
Sr. Product Manager
@ MixMode | Remote, US
Corporate Intern - Information Security (Year Round)
@ Associated Bank | US WI Remote
Senior Offensive Security Engineer
@ CoStar Group | US-DC Washington, DC