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

61–70 of 78 posts

Re: OpenAI Privacy Filter

#61

Post by CityOfThrowaway »

traceroute66 wrote: post #34
CityOfThrowaway wrote: post #20

Earlier quoted context omitted.

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 p…

I think this is a bit dramatic of a comment. Credit card numbers relayed over the phone are not deterministic...

"four three uh let's see sorry my vision is bad six eight..."

Easy versions of problems are easy. But reality is messy.

And no, neither I nor anybody else is expecting a 50B parameter model to find every instance. But finding 90% or 95% or 99% is pretty good, and sufficiently good for many use cases.

Re: OpenAI Privacy Filter

#62

Post by frognumber »

ares623 wrote: post #45

This looks actually useful. But can someone help me understand how you address the non-perfect scores: "Privacy Filter achieves an F1 score of 96% (94.04% precision and 98.04% recall)." How would you actually use this if it can fail redacting 4% of the data. How do you reliably know which 4% failed?

This is not a tool which can be used to assume information is anonymized.

The way OpenAI describes it is ...

... concerning.

"Our goal is for models to learn about the world, not about private individuals. Privacy Filter helps make that possible." This means they're using sensitive PII to train models.

A smart AI will re-identify all the information -- including that in the 96% -- in a snap. That's already a solved problem.

Re: OpenAI Privacy Filter

#63

Post by billylo »

I ran a comparison using this OPF with what I have in clarity.evergreen-labs.org (it's a Tauri app with local PII redaction.)

A few things jump out:

1) Dates are aggressively redacted, creating false positives. 2) Non-English names are not working yet.

Re: OpenAI Privacy Filter

#64

Post by CityOfThrowaway »

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.

OTOH, if you're willing to accept human-level error rates... why would you not do so at a burst-scalable task per minute and 1/1000th the cost?

I've built large human data entry operations. Variable throughput, monotony, hiring and perf management and firing, management, quality management. All of these things are large investments of human effort and money.

If I can achieve the same quality level (or in some use cases, even slightly degraded output) with software scaling characteristics and costs... I see zero reasons outside regulatory compliance reasons to have people do it.

Re: OpenAI Privacy Filter

#65

Post by CMay »

Just so people are clear, these types of models are almost universally naive and basic. If all you have is a single generic neutral message, "Hi, this is Bob.", it will be sufficient in most cases. If you have a pile of data, I am not aware of any PII redaction tool that has factored in all of the risks to identity leakage.

The problem is when companies use things like this and somehow believe they are anonymizing the data. No, you are not.

Still, for scenarios where the processed data isn't being directly published or shared, but used as some intermediate step like moderation enforcement, human evaluation layers or model training it can be useful to filter these things out.

Re: OpenAI Privacy Filter

#66

Post by benmann »

I welcome this release. Lots of good reasons to have these models and practices in place, even outside regulated industries. Even the EU AI act make some of this encessary (in theory). I've built redaction and rehydration through specilized NER models into https://grepture.com, so definitely adding this to the pipeline. Optionally sitting in the hot path, allowing actual tinkering with requests before/after they hit the LLM can be really handy for compliance or dircet user input scenarios.

Re: OpenAI Privacy Filter

#68

Post by codethief »

blfr wrote: post #51
fzxu22 wrote: post #37

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…

This is very cool because it allows you to use any model. Obviously, it still lets the model and its operator see the entire context of the conversation. I quite like Moxie's Confer[1] approach to just encrypt the whole thing in such a way that no one except the end-user sees the plaintext. [1] https://confer.to/

It's a nice approach – if only Intel SGX were more trustworthy.

Re: OpenAI Privacy Filter

#70

Post by fzxu22 »

stingraycharles wrote: post #49
fzxu22 wrote: post #37

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…

How does it handle “unredaction” in responses? E.g. let’s say the LLM does something with the document. You redacted its input, so it emits redacted content. Now what?

The proxy keeps 2-way mapping of identified PII and the redaction e.g. Jane Doe so the process is reversable i.e. redactions from LLM response will be replaced back to the original, and it should feel transparent on user end. I'll add more detailed example in README to make it clear.
Post reply on HN