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

21–30 of 78 posts

Re: OpenAI Privacy Filter

#21

Post by Everdred2dx »

LatencyKills wrote: post #18
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.

Yep, and already has been done.

https://github.com/chiefautism/privacy-parser

Re: OpenAI Privacy Filter

#24

Post by ori_b »

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.

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.

Re: OpenAI Privacy Filter

#26

Post by pigpag »

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.

[dead]

Re: OpenAI Privacy Filter

#27

Post by hiAndrewQuinn »

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.

For the confused: this link must have gotten revived or something, I posted this comment a few days ago. Looks like it's getting the accolades I claim it deserves now.

Re: OpenAI Privacy Filter

#28

Post by nl »

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.

Re: OpenAI Privacy Filter

#29

Post by yjftsjthsd-h »

LatencyKills wrote: post #18
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.

If you have the redacted and unredacted versions, then you can diff them; that seems unsurprising? Unless I'm really misunderstanding "spans"?

Re: OpenAI Privacy Filter

#30

Post by tanelpoder »

hiAndrewQuinn wrote: post #27
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.

For the confused: this link must have gotten revived or something, I posted this comment a few days ago. Looks like it's getting the accolades I claim it deserves now.

It was put into second-chance pool by moderators. I originally submitted this link a few days ago and today got this (semi?)automated email from HN, an excerpt below:

  The submission "OpenAI Privacy Filter" that you posted to Hacker News (https://news.ycombinator.com/item?id=47870901) looks good, but hasn't had much attention so far. We put it in the second-chance pool, so it will get a random placement on the front page some time in the next day or so.

  This is a way of giving good HN submissions multiple chances at the front page. If you're curious, you can read about it at https://news.ycombinator.com/item?id=26998308 and other links there.
Post reply on HN