As long as your training data itself isn't sensitive. If that's e.g. photos of products and you're training a quality assurance photo recognition software, that's probably fine, if it's unredacted support tickets, not fine.

▲

woodson 4 days ago | parent [-]

You can process your data through some learned feature extractor offline first, just to be sure.

▲

jszymborski 4 days ago | parent [-]

I used to work at a company who used to do this, but I'd argue that it almost never does what you want re: concealing the input space. There are so many ways to recover the input space from the latents, and often they are constructed expressly to contain exactly enough information to do precisely that.

	▲	fc417fc802 4 days ago \| parent [-]
		But how much effort would that require? ... is what I was going to say but in this age of "claude reverse engineer this doohickey" maybe the better question is how much compute and how many tokens it would require.