I just developed and deployed the first real-time protection for lemmy against CSAM!
I just developed and deployed the first real-time protection for lemmy against CSAM!
In the past months, there's a been a issue in various instances where accounts would start uploading blatant CSAM to popular communities. First of all this traumatizes anyone who gets to see it before the admins get to it, including the admins who have to review to take it down. Second of all, even if the content is a link to an external site, lemmy sill caches the thumbnail and stores it in the local pict-rs, causing headaches for the admins who have to somehow clear that out. Finally, both image posts and problematic thumbnails are federated to other lemmy instances, and then likewise stored in their pict-rs, causing such content to be stored in their image storage.
This has caused multiple instances to take radical measures, from defederating liberaly, to stopping image uploads to even shutting down.
Today I'm happy to announce that I've spend multiple days developing a tool you can plug into your instance to stop this at the source: pictrs-safety
Using a new feature from pictr-rs 0.4.3 we can now cause pictrs to call an arbitary endpoint to validate the content of an image before uploading it. pictrs-safety builds that endpoint which uses an asynchronous approach to validate such images.
I had already developed fedi-safety which could be used to regularly go through your image storage and delete all potential CSAM. I have now extended fedi-safety to plug into pict-rs safety and scan images sent by pict-rs.
The end effect is that any images uploaded or federated into your instance will be scanned in advance and if fedi-safety thinks they're potential CSAM, they will not be uploaded to your image storage at all!
This covers three important vectors for abuse:
- Malicious users cannot upload CSAM to for trolling communities. Even novel GenerativeAI CSAM.
- Users cannot upload CSAM images and never submit a post or comment (making them invisible to admins). The images will be automatically rejected during upload
- Deferated images and thumbnails of CSAM will be rejected by your pict-rs.
Now, that said, this tool is AI-driven and thus, not perfect. There will be false positives, especially around lewd images and images which contain children or child-topics (even if not lewd). This is the bargain we have to take to prevent the bigger problem above.
By my napkin calculations, false positive rates are below 1%, but certainly someone's innocent meme will eventually be affected. If this happen, I request to just move on as currently we don't have a way to whitelist specific images. Don't try to resize or modify the images to pass the filter. It won't help you.
For lemmy admins:
- pictrs-safety contains a docker-compose sample you can add to your lemmy's docker-compose. You will need to your put the .env in the same folder, or adjust the provided variables. (All kudos to @Penguincoder@beehaw.org for the docker support).
- You need to adjust your pict-rs ENVIRONMENT as well. Check the readme.
- fedi-safety must run on a system with GPU. The reason for this is that lemmy provides just a 10-seconds grace period for each upload before it times out the upload regardless of the results. A CPU scan will not be fast enough. However my architecture allows the fedi-safety to run on a different place than pictrs-safety. I am currently running it from my desktop. In fact, if you have a lot of images to scan, you can connect multiple scanning workers to pictrs-safety!
- For those who don't have access to a GPU, I am working on a NSFW-scanner which will use the AI-Horde directly instead and won't require using fedi-safety at all. Stay tuned.
For other fediverse software admins
fedi-safety can already be used to scan your image storage for CSAM, so you can also protect yourself and your users, even on mastodon or firefish or whatever.
I will try to provide real-time scanning in the future for each software as well and PRs are welcome.
Divisions by zero
This tool is already active now on divisions by zero. It's usage should be transparent to you, but do let me know if you notice anything wrong.
Support
If you appreciate the priority work that I've put in this tool, please consider supporting this and future development work on liberapay:
All my work is and will always be FOSS and available for all who need it most.
You're viewing a single thread.
Permanently Deleted
A 1% false positive rate is probably going to be to high to reliability report every positive to the FBI. The rate of actual CSAM is likely to be much lower than this. If it's 1 in 10,000 uploads, you will have 100 false positives and 1 true positive.
How can you possibly know what that the actual rate of CSAM is and claim it to be some stable figure considering anyone can easily come in, raid, and fuck up that figure?
Anti-CSAM detectors could also be used to better thin out false positives no? In other words, a detector for regular content. If we know one side of the coin, why not flip flop back and forth like a filtration system works irl to shake things out better? Even better why not only use that setup for reports going to the FBI and keep the OG setup for lemmy instances as we don’t care that much about false positives if it’s to protect children?
Permanently Deleted
That's a possibility. I would be concerned that the false positive rate is so high compared to the rate of actual CSAM that the FBI would just block anyone using this for reporting as spam.
What might be done is to track the detection rate of users. If anyone is significantly higher than the average they might be uploading CSAM. Only issue I see with this is the detector doesn't have an equal false positive rate across all content. It could be that the user just uploads pictures of their kids playing at the park a lot.
It doesn't have false positive across all content. It just tend to also sometimes catch some normal porn and some child context stuff as well
They always "could", I doubt anyone engaged in this sort of behavior is exposed enough to be found out while trolling. Legitimate question, also – wouldn't a report to the FBI exclusively impact US citizens, thus be easily avoided by "certain nationalities"? I know the international coalition for investigation exists, but afaik they're more so focused on active search rather than passive leads.
Permanently Deleted