This is a post by Abbey Chaver from Coefficient Giving (formerly Open Philanthropy). I recently did a relatively shallow investigation on the state of Infosec x AI. My research consisted of identifying the main GCR-relevant workstreams, looking at relative neglectedness, and trying to understand what skills were most needed to make progress.
The post below reflects this research and my opinions, and shouldn’t be seen as an official cG position.
Summary
- There are several high impact, neglected problems that need cybersecurity work. Specifically, I think that more people should work on what I call the AI Infrastructure Security Shortlist:
- Securing model confidentiality and integrity
- Authorization solutions for misuse
- Secure compute verification
- Protocols for securely using untrusted AI labor
- Preventing, detecting, and responding
... (read 1672 more words →)
Great course! Thanks for the writeup, Roy.
I'm a grantmaker at cG, and we'd be excited to see more universities put on this seminar! If you're a faculty member or graduate student at a research university and interested in running a version of this course, please fill out this interest form. We may be able to help with administrative costs.