ai-prompt-hacking-and-jailbreaking-llms.md

title	date	tags	aliases
2024-05-01 - TIL - AI Prompt Hacking and Jailbreaking LLMs	2024-05-01 09:43:55 -0700	ai-prompt-hacking-and-jailbreaking-llms resources til	today-i-learned things-i-learned

2024-05-01 - TIL - AI Prompt Hacking and Jailbreaking LLMs

Resources on AI Prompt Hacking and Jailbreaking LLMs.

Exercises

• Test your prompting skills to make Gandalf reveal secret information
• Predecessor of the Gandalf Exercise

Slides

• LLM Threats: Prompt Injections and Jailbreak Attacks
• A Primer on LLM Security: Hacking Large Language Models for Beginners
• "I want a slide deck on an intro to jailbreaking LLMs and prompt hacking" - SlidesGPT AI Generated PowerPoint

Learning Resources

• Prompt Injection
• Prompt Leaking
• Jailbreaking

Use Cases

• Learn about AI Prompt Hacking and Jailbreaking LLMs
• Practice applying what you've learned in a safe, secure, and legal way

References

• Learn Prompting: Your Guide to Communicating with AI
• SlidesGPT AI PowerPoint Generator Powered by ChatGPT API
• Vulnerable LLM Applications · OWASP/www-project-top-10-for-large-language-model-applications Wiki
• OWASP Top 10 for Large Language Model Applications | OWASP Foundation