Picture for Christoph Endres

Christoph Endres

Soft Begging: Modular and Efficient Shielding of LLMs against Prompt Injection and Jailbreaking based on Prompt Tuning

Add code
Jul 03, 2024
Viaarxiv icon

More than you've asked for: A Comprehensive Analysis of Novel Prompt Injection Threats to Application-Integrated Large Language Models

Add code
Feb 23, 2023
Viaarxiv icon