9 comments

  • mentalgear 5 hours ago
    SuperagentLM made available on-edge PPI redaction models already a few years ago in sizes 20B, 3B, 200M. They still seem to be available via their legacy API - well worth checking out to compare against this one. https://docs.superagent.sh/legacy/llms/superagent-lm-redact-...
  • hiAndrewQuinn 1 day ago
    I'm surprised nobody else has commented on this. This is a very straightforward and useful thing for a small locally runnable model to do.
    • apothegm 1 day ago
      And also something that it’s dangerous to try to do stochastically.
      • hiAndrewQuinn 1 day ago
        It's going to be stochastic in some sense whether you want it to be or not, human error never reaches zero percent. I would bet you a penny you'd get better results doing one two-second automated pass + your usual PII redaction than your PII redaction alone.
        • cyanydeez 1 day ago
          I think the problem is most secrets arn't stochastic; they're determinant. When the user types in the wrong password, it should be blocked. Using a probabilistic model suggests an attacker only now needs to be really close, but not correct.

          Sure, there's some math that says being really close and exact arn't a big deal; but then you're also saying your secrets don't need to be exact when decoding them and they absolutely do atm.

          Sure looks like a weird privacy veil that sorta might work for some things, like frosted glass, but think of a toilet stall with all frosted glass, are you still comfortable going to the bathroom in there?

      • moralestapia 22 hours ago
        The alternative being?
    • ashwindharne 1 day ago
      Same here, this is an incredibly useful thing to have in the toolkit
  • aubinkure 21 hours ago
    Exciting! I took a look through the code and found what appear to be the entity types for future releases - this release (V2 config) supports 8 entity types, but the V4 and V7 taxonomies have >20, mostly more personal ID types. Given this is a preview release, I imagine they'll release these.

    Details in my review article here: https://piieraser.ai/blog/openai-privacy-filter. Disclaimer: I also build PII detection systems.

  • stratos123 1 day ago
    There's some interesting technical details in this release:

    > Privacy Filter is a bidirectional token-classification model with span decoding. It begins from an autoregressive pretrained checkpoint and is then adapted into a token classifier over a fixed taxonomy of privacy labels. Instead of generating text token by token, it labels an input sequence in one pass and then decodes coherent spans with a constrained Viterbi procedure.

    > The released model has 1.5B total parameters with 50M active parameters.

    > [To build it] we converted a pretrained language model into a bidirectional token classifier by replacing the language modeling head with a token-classification head and post-training it with a supervised classification objective.

  • mplanchard 1 day ago
    It would be nice if their examples weren’t mostly things that are easy to catch with regex, but it’s cool to see if released as an open, local model.
  • Havoc 1 day ago
    50M effective parameters is impressively light. Is there a similarly light model on the prompt injection side? Most of the mainstream ones seem heavier
  • y0eswddl 1 day ago
    crying_laughing_emoji.gif

    yes, please, feed daddy AI all your PII

    • klauserc 1 day ago
      Was my first thought as well, but this is an open weights model. You can run it on your own hardware.
  • 7777777phil 1 day ago
    > The model is available today under the Apache 2.0 license on Hugging Face (opens in a new window) and Github (opens in a new window).

    Bringing back the Open to OpenAI..

  • ndom91 1 day ago
    Where's the gguf from Unsloth and co?