This list of resources is curated by Lakera to help you dive into Large Language Model (LLM) and Generative AI (GenAI) security in more depth - everything from articles, guides, and games to courses, open source tools, and research papers.

• Table of Contents

Articles

• Adversarial Attacks on LLMs
• The Rise of the Internet of Agents: A New Era of Cybersecurity
• Prompt injection: What’s the worst that can happen?
• AI Injections: Direct and Indirect Prompt Injections and Their Implications
• Reverse Prompt Engineering for Fun and (no) Profit
• Adding Fuel To The Fire: How effective are LLM-based safety filters for AI systems?
• Plugin Vulnerabilities: Visit a Website and Have Your Source Code Stolen
  • A practical exploit of ChatGPT with plugins
• Hacking Google Bard - From Prompt Injection to Data Exfiltration
  • A practical exploit of Google Bard with the Gmail plugin
• The ‘ petertodd’ phenomenon
  • About “glitch tokens” - rare tokens that make GPT behave in weird ways

Guides

• The ELI5 Guide to Prompt Injection: Techniques, Prevention Methods & Tools
• The Beginner's Guide to Visual Prompt Injections: Invisibility Cloaks, Cannibalistic Adverts, and Robot Women
• LLM Security Playbook
• Prompt Injection Attacks Handbook
• Adversarial Prompting in LLMs
• Real World LLM Exploits