Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

OpenAI Privacy Filter

openai.com

Post reply on HN
Print view View original

31–40 of 78 posts

Re: OpenAI Privacy Filter

#31

Post by stingraycharles »

nl wrote: post #28

I'm no where near as smart as OpenAI of course, but I did build https://tools.nicklothian.com/webner/index.html that uses a BERT based named-entity-recognition model running in your browser to do a subset of PII redaction. It works pretty well for the use cases I was playing with. The OpenAI model is small enough that I might enhance my tool to use it.

I just used it on a document, but the amount of false positives this generates make it faily difficult to use?

I fed it a ~ 100 line markdown document, took about 10 seconds, and it decided that "matter" (as in, frontmatter), "end" (as in, frontend), MCP (as in, mcp server) are organizations.

Most of them don't even make grammatical sense, e.g. "Following the discussion in , blahblah".

Brings me back to what NLP was like a decade ago. I always thought spaCy was a very nice project in that space.

Re: OpenAI Privacy Filter

#33

Post by nl »

stingraycharles wrote: post #31
nl wrote: post #28

I'm no where near as smart as OpenAI of course, but I did build https://tools.nicklothian.com/webner/index.html that uses a BERT based named-entity-recognition model running in your browser to do a subset of PII redaction. It works pretty well for the use cases I was playing with. The OpenAI model is small enough that I might enhance my tool to use it.

I just used it on a document, but the amount of false positives this generates make it faily difficult to use? I fed it a ~ 100 line markdown document, took about 10 seconds, and it decided that "matter" (as in, frontmatter), "end" (as in, frontend), MCP (as in, mcp server) are organizations. Most of them don't even make grammatical sense, e.g. "Following the discussion in , blahblah". Brings me back to what NLP was…

Yeah this really is roughly NLP ~10 years ago.

It does work better on plain text than markdown because of casing. I can't see what you used (kinda the point - because it run all in your browser) but if you can share the markdown as a gist or something I can take a look and comment more concretely.

Re: OpenAI Privacy Filter

#34

Post by traceroute66 »

CityOfThrowaway wrote: post #20
cyanydeez wrote: post #11

Earlier quoted context omitted.

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 absolu…

I dunno what use case you're thinking this is for. The use case for this is that many enterprise customers want SaaS products to strip PII from ingested content, and there's no non-model way to do it. Think, ingesting call transcripts where those calls may include credit card numbers or private data. The call transcripts are very useful for various things, but for obvious reasons we don't want to ingest the PII.

> Think, ingesting call transcripts where those calls may include credit card numbers or private data. The call transcripts are very useful for various things, but for obvious reasons we don't want to ingest the PII.

Credit card numbers are deterministic. A five year old could write a script to strip out credit card numbers.

As for other PII ? You're seriously expecting an LLM to find every instance of every random piece of PII ? Worldwide ? In multiple languages ? I've got an igloo I'd like to sell you ...

Re: OpenAI Privacy Filter

#35

Post by pros »

freakynit wrote: post #22

Can someone explaon how can I reconstruct the original entities back if there are, for example, more than one person names?

You cannot — not with the model alone. It gives you spans + types, not identity.

You need to do that part yourself after the model runs. The filter gives you spans; for each one, assign a stable ID (PERSON_1, PERSON_2) and keep {PERSON_1: "Harry", PERSON_2: "Ron"} next to the document. Swap IDs in before the LLM call, swap originals back in the reply.

Scoping that map to a document/project keeps the same person consistent across calls, so Harry stays PERSON_1 instead of becoming PERSON_3 the next time he's mentioned.

(Disclosure: I'm building a Mac privacy tool, RedMatiq, that does exactly this. The mapping layer turned out substantially harder than detection.)

Re: OpenAI Privacy Filter

#36

Post by flashdesk »

This is where stochastic approaches start to feel a bit uncomfortable.

Even small mistakes can make something dealing with sensitive data hard to trust. It seems useful as a first pass, but I’d probably still want some deterministic checks or a human in the loop to feel confident using it.

Re: OpenAI Privacy Filter

#37

Post by fzxu22 »

Working on this: https://github.com/KevinXuxuxu/anon_proxy, a sort of anonymization proxy to use with LLM providers. It does model (OpenAI privacy filter) + regex PII detection, and replaces them back-and-forth for API requests and responses. With locally hosted detection model, no PII leaves your local environment. I find it very useful especially when you're working on sensitive documents (legal, tax, immigration etc.), hope you find it helpful as well :)

Re: OpenAI Privacy Filter

#38

Post by fathermarz »

flashdesk wrote: post #36

This is where stochastic approaches start to feel a bit uncomfortable. Even small mistakes can make something dealing with sensitive data hard to trust. It seems useful as a first pass, but I’d probably still want some deterministic checks or a human in the loop to feel confident using it.

I built a community tool for exactly this, based on privacy first principals but around the what. It’s workflow based and not “put your sensitive data into ChatGPT and hope it captures the right stuff”. Mostly built for security folks but anyone can use it

Check it out: https://redact.cabreza.com

Re: OpenAI Privacy Filter

#40

Post by creesch »

ori_b wrote: post #24
hiAndrewQuinn wrote: post #6

Earlier quoted context omitted.

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.

The advantage of computers was that they didn't make human errors; they did things repeatedly, quickly, and predictably. If I'm going to accept human error, I'd like it to come from a human.

> The advantage of computers was that they didn't make human errors;

Sure they do, computers repeatedly, quickly, and predictably do what they are programmed to do. Which includes any human errors in that programming.

Post reply on HN