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:

https://liberapay.com/db0/

All my work is and will always be FOSS and available for all who need it most.

  • gamer@lemm.ee
    ·
    1 year ago

    I think you're confused by the purpose of that statement. When the authors say not to use it for anything important, they're basically trying to waive liability (informally). It's kind of like how every open source license has a statement like:

    THE SOFTWARE IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED ...

    If you use an open source project for air traffic control software, and a bug causes a bunch of people to die, that's your fault, not the author of the software. The CLIP people are essentially saying that you shouldn't use their software to build something that requires a lot of accuracy since it probably wasn't designed to be as accurate as you need it to be.

    But what I'm wondering is why you're being so dramatic about this. You're claiming that it's highly dangerous/reckless/risky to use it, yet hand waving over the why.

    • steventrouble@programming.dev
      ·
      1 year ago

      I think you’re confused by the purpose of that statement.

      That's not the statement I'm referring to. This is the statement I'm referring to:

      Any deployed use case of the model - whether commercial or not - is currently out of scope. Non-deployed use cases such as image search in a constrained environment, are also not recommended unless there is thorough in-domain testing of the model with a specific, fixed class taxonomy. This is because our safety assessment demonstrated a high need for task specific testing especially given the variability of CLIP’s performance with different class taxonomies. This makes untested and unconstrained deployment of the model in any use case currently potentially harmful.

      Source: https://huggingface.co/openai/clip-vit-large-patch14

      It's dangerous for the same reason you shouldn't use tin foil for load bearing struts. There's a reason that the creators of websites are required to block CSAM, and using half-baked tooling that doesn't work is blatantly skirting around the issue.