Post Ad3EDYA4M9PzMDLk4e by alex@cybervillains.com
 (DIR) More posts by alex@cybervillains.com
 (DIR) Post #Ad3EDVyIUwoUZ7pJRo by alex@cybervillains.com
       2023-12-20T15:58:47Z
       
       0 likes, 1 repeats
       
       How does Stable Diffusion 1.5 know how to create CSAM? It turns out it was trained on thousands of illegal images contained in the extremely popular LAION-5B image set.I’m so incredibly proud of my friend and colleague  @det Story: https://www.404media.co/laion-datasets-removed-stanford-csam-child-abuse/ Paper: https://stacks.stanford.edu/file/druid:kh752sm9123/ml_training_data_csam_report-2023-12-20.pdf
       
 (DIR) Post #Ad3EDYA4M9PzMDLk4e by alex@cybervillains.com
       2023-12-20T15:59:06Z
       
       0 likes, 0 repeats
       
       Lots of people have worried about CSAM in training sets, including the LAION team themselves, but David actually created a novel mechanism to detect it.Hopefully this will change the way these training sets are created in the future.@det