Artwork

Content provided by Changelog Media. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Changelog Media or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://player.fm/legal.
Player FM - Podcast App
Go offline with the Player FM app!

Threat modeling LLM apps

54:40
 
Share
 

Manage episode 435570456 series 2385063
Content provided by Changelog Media. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Changelog Media or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://player.fm/legal.

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.

Leave us a comment

Changelog++ members save 9 minutes on this episode because they made the ads disappear. Join today!

Sponsors:

  • Assembly AI – Turn voice data into summaries with AssemblyAI’s leading Speech AI models. Built by AI experts, their Speech AI models include accurate speech-to-text for voice data (such as calls, virtual meetings, and podcasts), speaker detection, sentiment analysis, chapter detection, PII redaction, and more.
  • Porkbun – Go to porkbun.com to get .app, .dev, or .foo domain names at Porkbun for only $1 for the first year!
  • Changelog News – A podcast+newsletter combo that’s brief, entertaining & always on-point. Subscribe today.

Featuring:

Show Notes:

Something missing or broken? PRs welcome!

  continue reading

Chapters

1. Welcome to Practical AI (00:00:00)

2. Sponsor: Assembly AI (00:00:35)

3. Donato's journey in gen AI (00:04:10)

Chapter image

4. The most secure LLM (00:07:11)

5. What is a threat model? (00:08:58)

6. Commonplace AI security (00:10:38)

7. Setting up guard rails (00:14:20)

8. Sponsor: Porkbun (00:22:34)

9. Model checking (00:24:48)

10. Closed LLM endpoints (00:34:17)

11. input & output validation (00:37:17)

12. Sponsor: Changelog News (00:41:32)

13. RLHF in alignment (00:43:19)

14. Jailbreakers vs aligners (00:46:37)

15. Exciting things to explore (00:50:25)

16. Thanks for listening! (00:53:24)

17. Outro (00:53:51)

285 episodes

Artwork
iconShare
 
Manage episode 435570456 series 2385063
Content provided by Changelog Media. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Changelog Media or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://player.fm/legal.

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.

Leave us a comment

Changelog++ members save 9 minutes on this episode because they made the ads disappear. Join today!

Sponsors:

  • Assembly AI – Turn voice data into summaries with AssemblyAI’s leading Speech AI models. Built by AI experts, their Speech AI models include accurate speech-to-text for voice data (such as calls, virtual meetings, and podcasts), speaker detection, sentiment analysis, chapter detection, PII redaction, and more.
  • Porkbun – Go to porkbun.com to get .app, .dev, or .foo domain names at Porkbun for only $1 for the first year!
  • Changelog News – A podcast+newsletter combo that’s brief, entertaining & always on-point. Subscribe today.

Featuring:

Show Notes:

Something missing or broken? PRs welcome!

  continue reading

Chapters

1. Welcome to Practical AI (00:00:00)

2. Sponsor: Assembly AI (00:00:35)

3. Donato's journey in gen AI (00:04:10)

Chapter image

4. The most secure LLM (00:07:11)

5. What is a threat model? (00:08:58)

6. Commonplace AI security (00:10:38)

7. Setting up guard rails (00:14:20)

8. Sponsor: Porkbun (00:22:34)

9. Model checking (00:24:48)

10. Closed LLM endpoints (00:34:17)

11. input & output validation (00:37:17)

12. Sponsor: Changelog News (00:41:32)

13. RLHF in alignment (00:43:19)

14. Jailbreakers vs aligners (00:46:37)

15. Exciting things to explore (00:50:25)

16. Thanks for listening! (00:53:24)

17. Outro (00:53:51)

285 episodes

All episodes

×
 
Loading …

Welcome to Player FM!

Player FM is scanning the web for high-quality podcasts for you to enjoy right now. It's the best podcast app and works on Android, iPhone, and the web. Signup to sync subscriptions across devices.

 

Quick Reference Guide