Learn PromptingFiltragem
Filtragem é uma técnica comum para prevenir a manipulação do prompt. Existem alguns tipos de filtragem, mas a ideia básica é verificar palavras e frases no prompt inicial ou na saída que devem ser proibidas. Você pode usar uma lista negra (blacklist) ou até mesmo uma lista branca (whitelist) para esse propósito. Uma lista negra é uma lista de palavras e frases que devem ser proibidas, enquanto uma lista branca é uma lista de palavras e frases que devem ser permitidas.
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
-
Kang, D., Li, X., Stoica, I., Guestrin, C., Zaharia, M., & Hashimoto, T. (2023). Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks. ↩
-
Selvi, J. (2022). Exploring Prompt Injection Attacks. https://research.nccgroup.com/2022/12/05/exploring-prompt-injection-attacks/ ↩