From the source
OpenAI states that LLMs are susceptible to prompt injections, jailbreaks, and other attacks that allow adversaries to overwrite a model's original instructions.
The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
Research paper
From the source
Today's LLMs are susceptible to prompt injections, jailbreaks, and other attacks that allow adversaries to overwrite a model's original instructions with their own malicious prompts.
openai.com
