Guarding LLM and NLP APIs: A Trailblazing Odyssey for Enhanced Security - Podcast #190

Guarding LLM and NLP APIs: A Trailblazing Odyssey for Enhanced Security - Podcast #190

MLOps.community via YouTube Direct link

[] Toxic data for LLMs

23 of 24

23 of 24

[] Toxic data for LLMs

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Guarding LLM and NLP APIs: A Trailblazing Odyssey for Enhanced Security - Podcast #190

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

  1. 1 [] Ads' preferred coffee
  2. 2 [] Takeaways
  3. 3 [] Please like, share, and subscribe to our MLOps channels!
  4. 4 [] Security and vulnerabilities
  5. 5 [] Work at Cohere and OWASP
  6. 6 [] Previous work vs LLMs Companies
  7. 7 [] LLM vulnerabilities
  8. 8 [] Good qualities to combat prompt injection problems
  9. 9 [] Data lineage
  10. 10 [] Red teaming
  11. 11 [] Freakiest LLM vulnerabilities
  12. 12 [] Severe Autonomy Concerns
  13. 13 [] Hallucinations
  14. 14 [] Prompt injection
  15. 15 [] Vector attacks to be recognized
  16. 16 [] LLMs being customed
  17. 17 [] Security changes due to maturity
  18. 18 [] OWASP Top 10 for Large Language Model Applications
  19. 19 [] Gandalf game
  20. 20 [] Prompt injection attack
  21. 21 [] Overlapping security
  22. 22 [] Data poisoning
  23. 23 [] Toxic data for LLMs
  24. 24 [] Wrap up

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.