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
Social Engineer For Reverse Engineering Exploit Study
@ Independent study | Remote
Cloud Security Analyst
@ Cloud Peritus | Bengaluru, India
Cyber Program Manager - CISO- United States – Remote
@ Stanley Black & Decker | Towson MD USA - 701 E Joppa Rd Bg 700
Network Security Engineer (AEGIS)
@ Peraton | Virginia Beach, VA, United States
SC2022-002065 Cyber Security Incident Responder (NS) - MON 13 May
@ EMW, Inc. | Mons, Wallonia, Belgium
Information Systems Security Engineer
@ Booz Allen Hamilton | USA, GA, Warner Robins (300 Park Pl Dr)