Threat modeling LLM apps (Practical AI #283)
If you have questions at the intersection of Cybersecurity and AI, you need to know Donato at WithSecure! Donato has been threat modeling AI applications and seriously applying those models in his day-to-day work. He joins us in this episode to discuss his LLM application security canvas, prompt injections, alignment, and more.
Embed this episode
Chapters
- 0:00 Welcome to Practical AI
- 0:35 Sponsor: Assembly AI
- 4:10 Donato's journey in gen AI
- 7:11 The most secure LLM
- 8:58 What is a threat model?
- 10:38 Commonplace AI security
- 14:20 Setting up guard rails
- 22:34 Sponsor: Porkbun
- 24:48 Model checking
- 34:17 Closed LLM endpoints
- 37:17 input & output validation
- 41:32 Sponsor: Changelog News
- 43:19 RLHF in alignment
- 46:37 Jailbreakers vs aligners
- 50:25 Exciting things to explore
- 53:24 Thanks for listening!
- 53:51 Outro
No transcript yet.
Frequently asked questions
How long is this episode of Changelog Master Feed?
This episode is 54 minutes long.
When was this Changelog Master Feed episode published?
This episode was published on August 22, 2024.
Is there a transcript available for this episode?
Yes, a full transcript is available for this episode. You can read the complete transcript on the episode page.
Can I download this Changelog Master Feed episode?
Yes. Use the download control on the episode player to save the publisher-provided media file.