My reading of this is the TEE is used to validate the binary hasn’t been tampered with, but the TEE is definitely not powerful enough to do any inference.
The provider process is hardened against common local inspection paths, including debugger attachment and external memory inspection. The integrity of the running binary is also part of the trust model, helping ensure that the software serving requests matches what the network expects.
The system also uses hardware-backed attestation rooted in Apple’s security architecture. Secure Enclave keys, attestation signals, and recurring challenge-response checks are used to verify that a participating node is running with the expected protections and software state.
I haven’t fact-checked this, but the TEE could protect GPU memory in addition to main memory. Apple attests that the correct binary is running in the TEE, et voila.
The binary performing the inference isn’t running in the TEE, because the TEE runs on a weaker processor.
The TEE is validating that the binary running on the main processors hasn’t been tampered with
That’s decent, but doesn’t match the statement that inference is happening in the TEE
I think the phrase “running in the TEE” is the idiomatic way to describe a program running on the main CPU, attested by the TEE processor, and protected/isolated from other processes on the system (modulo exploits, lol). I’m vaguely familiar with AMD’s SEV-SNP, mainly from reading security papers rather than any hands-on experience. I make no claims about Apple’s Secure Enclave, though.
think the phrase “running in the TEE” is the idiomatic way to describe a program running on the main CPU
In the Confidentiality/Integrity/Availability triangle, a secondary process running in another operating system gives you integrity, but not confidentiality
They lay out all the protections they have in place to ensure private prompt execution. The TEE is used to validate the integrity of the binary, and they use other protections like E2EE, SEV-SNP on the coordinator, MacOS security protections (hardened runtime, SIP, kernel protections, etc), plus (from what i can tell an optional enrollment from providers) in Apple’s MDM which makes Apple verify the integrity of the system.
There’s no way that’s possible
My reading of this is the TEE is used to validate the binary hasn’t been tampered with, but the TEE is definitely not powerful enough to do any inference.
I haven’t fact-checked this, but the TEE could protect GPU memory in addition to main memory. Apple attests that the correct binary is running in the TEE, et voila.
Attesting is very different from protecting
The binary performing the inference isn’t running in the TEE, because the TEE runs on a weaker processor. The TEE is validating that the binary running on the main processors hasn’t been tampered with
That’s decent, but doesn’t match the statement that inference is happening in the TEE
I think the phrase “running in the TEE” is the idiomatic way to describe a program running on the main CPU, attested by the TEE processor, and protected/isolated from other processes on the system (modulo exploits, lol). I’m vaguely familiar with AMD’s SEV-SNP, mainly from reading security papers rather than any hands-on experience. I make no claims about Apple’s Secure Enclave, though.
I very much disagree with
In the Confidentiality/Integrity/Availability triangle, a secondary process running in another operating system gives you integrity, but not confidentiality
You both should just read the docs
https://docs.darkbloom.dev/security/overview
They lay out all the protections they have in place to ensure private prompt execution. The TEE is used to validate the integrity of the binary, and they use other protections like E2EE, SEV-SNP on the coordinator, MacOS security protections (hardened runtime, SIP, kernel protections, etc), plus (from what i can tell an optional enrollment from providers) in Apple’s MDM which makes Apple verify the integrity of the system.
That’s literally what I said, and why I disagreed with the other poster saying it ran in the TEE
Whether the protections of the main binary are sufficient I’ve made no comment on