nsfwjs

Follow-up question: what work has been done on client-side moderation? I know this gets dangerously close to the kind of content scanning that eg apple has tried (to very detrimental results), but hear me out: I really think this is a prerequisite to end-to-end encryption on a social network (there has to be some level of protection; even if 100% of users report 100% of bad content, imagine scrolling a feed and stumbling upon CSAM simply because you were the first person to see it). I also also think it's possible to strike a balance that preserves user agency while still protecting them, by simply inserting a manual reporting step. So, for example, potentially problematic content gets put behind an interstitial with a content warning and options to view, hide, report, etc. But again, this requires client-side content classification. I'm

This would be interesting 2 years ago, but considering how long is available https://github.com/infinitered/nsfwjs and related https://github.com/nsfw-filter/nsfw-filter this seems just like Bumble's attempt to get into news.

can this help https://github.com/infinitered/nsfwjs

I was qurious about the classifier, and as expected it appears to be based on crawling to get the unsafe images - I doubt it's quite in compliance with neither copyright or gdpr.. The classifier lib: https://github.com/alex000kim/nsfw_data_scraper Announcement points to this data source (while the readme hints at a "premium" classifier): https://github.com/infinitered/nsfwjs

Also, 100% open source JS: https://github.com/infinitered/nsfwjs MODEL: https://github.com/gantman/nsfw_model