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

11–20 of 78 posts

Re: OpenAI Privacy Filter

#11

Post by cyanydeez »

hiAndrewQuinn wrote: post #6
apothegm wrote: post #4

Earlier quoted context omitted.

And also something that it’s dangerous to try to do stochastically.

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.

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?

Re: OpenAI Privacy Filter

#14

Post by moralestapia »

apothegm wrote: post #4
hiAndrewQuinn wrote: post #2

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.

And also something that it’s dangerous to try to do stochastically.

The alternative being?

Re: OpenAI Privacy Filter

#17

Post by JLO64 »

mplanchard wrote: post #13

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.

For my customers I use regexes to block them from potentially publishing personal emails/phone numbers to their websites but I really wouldn't mind running this in addition just for the extra peace of mind. I don't have a GPU on our server, but I hope this is light enough of a model to handle CPU only inference on less than 2k tokens at a time.

Re: OpenAI Privacy Filter

#18

Post by LatencyKills »

stratos123 wrote: post #9

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 Vit…

Couldn't this be used to locate private data in unstructured text without having to rely on other means of PII detection?

1. Pass the raw text through the filter to obtain the spans.

2. Map all the spans back to the original text.

Now you have all the PII information.

Re: OpenAI Privacy Filter

#20

Post by CityOfThrowaway »

cyanydeez wrote: post #11
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.

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.

Post reply on HN