How is it trivially detectable?

squeegeeninja 43 minutes ago | parent [-]

If (and that's a bit of an ask to be honest) I understand this correctly, the weights will look very different from what trained weights look like. Very sparse, not uniformly random.

	▲	Muromec 15 minutes ago \| parent [-]
		(tinfoil hat on) Hiding it better is the next capability described in the paper that could as well be classified.