One flaw with FHE is that it guarantees only that you need the key to see the inputs or outputs of the computation, but not necessarily that the computation is the one you want. For example, the computation could be adversarial for certain inputs, or an adversary could insert their own computation first (or last).

▲

noman-land an hour ago | parent [-]

100% not an expert but my understanding was that part of what you are proving by signing the computation is that the computation itself was performed specifically as agreed to. I may be mixing this up with zero knowledge proofs.

▲

LoganDark an hour ago | parent [-]

If this were the case it would be necessary to send the entire model weights in response to every request which would be a bit inconvenient.

	▲	drdeca 25 minutes ago \| parent [-]
		Hmm, could one instead of sending the model weights, send like, a merkle tree root for them, not exactly specifying the model, but at least demonstrating that the same model is used each time?