Learn PromptingEnclausuramento de Sequência Aleatória
Outra forma de defesa é enclausurar a entrada do usuário entre duas sequências aleatórias de caracteres. Tome este prompt como exemplo:
Traduza a seguinte entrada do usuário para o espanhol.
{{user_input}}
Ele pode ser aprimorado adicionando as sequências aleatórias:
Traduza a seguinte entrada do usuário para o espanhol (ela está enclausurada em strings aleatórias).
FJNKSJDNKFJOI
{{user_input}}
FJNKSJDNKFJOI
Sander Schulhoff
Sander Schulhoff is the CEO of HackAPrompt and Learn Prompting. He created the first Prompt Engineering guide on the internet, two months before ChatGPT was released, which has taught 3 million people how to prompt ChatGPT. He also partnered with OpenAI to run the first AI Red Teaming competition, HackAPrompt, which was 2x larger than the White House's subsequent AI Red Teaming competition. Today, HackAPrompt partners with the Frontier AI labs to produce research that makes their models more secure. Sander's background is in Natural Language Processing and deep reinforcement learning. He recently led the team behind The Prompt Report, the most comprehensive study of prompt engineering ever done. This 76-page survey, co-authored with OpenAI, Microsoft, Google, Princeton, Stanford, and other leading institutions, analyzed 1,500+ academic papers and covered 200+ prompting techniques.
Footnotes
-
Stuart Armstrong, R. G. (2022). Using GPT-Eliezer against ChatGPT Jailbreaking. https://www.alignmentforum.org/posts/pNcFYZnPdXyL2RfgA/using-gpt-eliezer-against-chatgpt-jailbreaking ↩