46 citations · 46 across the 2 of their papers we have counts for
Showing cs.CRShow all
2 papers · 1 filter
cs.CR2024
Soft Begging: Modular and Efficient Shielding of LLMs against Prompt Injection and Jailbreaking based on Prompt Tuning
Simon Ostermann, Kevin Baum, Christoph Endres +2
Prompt injection (both direct and indirect) and jailbreaking are now recognized as significant issues for large language models (LLMs), particularly due to their potential for harm…
cs.CR2023★ 46 cited
Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
Kai Greshake, Sahar Abdelnabi, Shailesh Mishra +3
Large Language Models (LLMs) are increasingly being integrated into various applications. The functionalities of recent LLMs can be flexibly modulated via natural language prompts.…