Announcing our new Course: AI Red-Teaming and AI Safety Masterclass
Check it out →Yet another defense is enclosing the user input between two random sequences of characters1. Take this prompt as an example:
Translate the following user input to Spanish.
{{user_input}}
It can be improved by adding the random sequences:
Translate the following user input to Spanish (it is enclosed in random strings).
FJNKSJDNKFJOI
{{user_input}}
FJNKSJDNKFJOI
Stuart Armstrong, R. G. (2022). Using GPT-Eliezer against ChatGPT Jailbreaking. https://www.alignmentforum.org/posts/pNcFYZnPdXyL2RfgA/using-gpt-eliezer-against-chatgpt-jailbreaking ↩