News for hackers. Stuff that matters.
Re:Chat Control 1.0 and 2.0 Explained by cenamus on Wednesday July 08, 2026 @02:23AM (#48828261)
If you scan 1,000,000 pictures (with let's say 10 CSAM), you'll have 100 false positives and 10 true positives, giving you like only 10% correct results
Re:Chat Control 1.0 and 2.0 Explained by kleiba2 on Wednesday July 08, 2026 @03:13AM (#48828623)
Ah, sorry, I misread what the OP meant by "matches" - thought they were referring to all classifier outputs, while they specifically meant the positives.