What is the false negative rate and total rates? Without those we are missing too much. If the false negative rate (saying fine but it isn't) then the whole thing is useless. If the total cases are a few hundred (either CASM isn't a problem or those doing it use other platforms cause they know they will be caught on these) I don't care much that some are false positives - odds are it didn't get me.

▲

tremon an hour ago | parent [-]

You can not know the false negative rate without investigating 100% of all photos. You are asking for the impossible.

	▲	fc417fc802 3 minutes ago \| parent \| next [-]
		Sure you can, random sampling should work. Don't just go making things up. Of course actually carrying out that experiment would be absurd since I don't think anyone expects an appreciable percentage of clearnet material to be CSAM. The working assumption is that the goal is to find a needle in a haystack so GP's objection about needing to know the false negative rate is misguided.
	▲	bluGill an hour ago \| parent \| prev [-]
		if you want perfection. But the eu should be doing investigation that they can use statistics to create a good estimate.