Getting AI to Do the Unexpected - Exploring LLM Vulnerabilities and Defenses

Getting AI to Do the Unexpected - Exploring LLM Vulnerabilities and Defenses

Conf42 via YouTube Direct link

defenses to sensitive information disclosure

23 of 27

23 of 27

defenses to sensitive information disclosure

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Getting AI to Do the Unexpected - Exploring LLM Vulnerabilities and Defenses

Automatically move to the next video in the Classroom when playback concludes

  1. 1 intro
  2. 2 preamble
  3. 3 agenda
  4. 4 who am i?
  5. 5 tax day is on april 15th!
  6. 6 what is an llm?
  7. 7 what is an llm used for?
  8. 8 what is prompt engineering?
  9. 9 zero shot prompting
  10. 10 few shot prompting
  11. 11 chain-of-thought prompting
  12. 12 attacks
  13. 13 owasp top 10 llm vulnerabilities
  14. 14 prompt injections
  15. 15 how do they play out in real-life
  16. 16 prompt leaking
  17. 17 prompt injection
  18. 18 1-step further
  19. 19 real world scenarios
  20. 20 defenses to prompt injections
  21. 21 insecure output handling
  22. 22 sensitive information disclosure
  23. 23 defenses to sensitive information disclosure
  24. 24 prompt jailbreaking
  25. 25 secure practices: audit logging
  26. 26 let's see it in action
  27. 27 thank you + links

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.