Speaker
Description
We aim to bootstrap some discussions on the intersections of the following topics:
- Agentic AI
- Confidential Computing (MC on this already exists)
- Attestation
- Attested TLS
To initiate discussion, I will present a few slides to introduce the above, then pose some open questions. We very much welcome presentations by attendees on related topics. If you are interested in presenting, please contact me with title and expected time.
Example questions for discussion:
1. Identity of AI agent
2. Software- vs. hardware-based attestation
3. PQ migration up to the hardware level
4. Geo-location of AI agent
5. Supply chain attacks
6. Security analysis for complex cases of CPU+GPU
7. Conflicting requirements of multiple stakeholders
• (Almost) every stakeholder claims to be out of TCB. How do we judge
it?
8. Trust and key management issues for AI agents
9. Bootstrapping issues for AI agents
10. Confidential Computing may be used by the adversary to secretly
offer bad services. How can we prevent such abuse cases?
11. Security analysis for layered implementation of AI agents
12. How is AI different from any other software?