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

Extracting AI models from mobile apps

altayakkus.substack.com

Post reply on HN
Print view View original

141–150 of 250 posts

Re: Extracting AI models from mobile apps

#141

Post by philwelch »

_DeadFred_ wrote: post #118
philwelch wrote: post #89

Earlier quoted context omitted.

You’re applying a double standard to LLM’s and human creators. Any human writer or artist or filmmaker or musician will be influenced by other people’s works, even while those works are still under copyright.

Human creators don't store that 'influence' in a digital machine accessible format generated directly from the copyrighted content though. Although with the 'good new everyone, we built the torment nexus' trajectory of AI my guess is at this point AI companies would just incorporate actual human brains instead of digital storage if that was the requirement.

Your argument boils down to “we don’t know how brains work”, and it is a non-sequitur. It isn’t a violation of copyright law to create original works under the creative influence of works still under copyright.

Re: Extracting AI models from mobile apps

#142

Post by dang »

jonpo wrote: post #16

Well done you seem to have liberated an open model trained on open data for blind and visually impaired people. Paper: https://arxiv.org/pdf/2204.03738 Code: https://github.com/microsoft/banknote-net Training data: https://raw.githubusercontent.com/microsoft/banknote-net/ref... model: https://github.com/microsoft/banknote-net/blob/main/models/b... Kinda easier to download it straight from github. Its licenced under M…

> But lets not let that get in the way of hating on AI shall we?

Can you please edit this kind of thing out of your HN comments? (This is in the site guidelines: https://news.ycombinator.com/newsguidelines.html.)

It leads to a downward spiral, as one can see in the progression to https://news.ycombinator.com/item?id=42604422 and https://news.ycombinator.com/item?id=42604728. That's what we're trying to avoid here.

Your post is informative and would be just fine without the last sentence (well, plus the snarky first two words).

Re: Extracting AI models from mobile apps

#143

Post by dang »

cess11 wrote: post #38
jonpo wrote: post #16

Well done you seem to have liberated an open model trained on open data for blind and visually impaired people. Paper: https://arxiv.org/pdf/2204.03738 Code: https://github.com/microsoft/banknote-net Training data: https://raw.githubusercontent.com/microsoft/banknote-net/ref... model: https://github.com/microsoft/banknote-net/blob/main/models/b... Kinda easier to download it straight from github. Its licenced under M…

[flagged]

Can you please edit swipes out of your HN comments? Your post would be fine with just the first sentence.

This is in the site guidelines: https://news.ycombinator.com/newsguidelines.html.

Re: Extracting AI models from mobile apps

#144

Post by dang »

TechDebtDevin wrote: post #101
jonpo wrote: post #16

Well done you seem to have liberated an open model trained on open data for blind and visually impaired people. Paper: https://arxiv.org/pdf/2204.03738 Code: https://github.com/microsoft/banknote-net Training data: https://raw.githubusercontent.com/microsoft/banknote-net/ref... model: https://github.com/microsoft/banknote-net/blob/main/models/b... Kinda easier to download it straight from github. Its licenced under M…

[flagged]

Please don't cross into personal attack or otherwise break the site guidelines when posting here. Your post would be fine with just the first sentence.

https://news.ycombinator.com/newsguidelines.html

Re: Extracting AI models from mobile apps

#147

Post by refulgentis »

ipsum2 wrote: post #47

This is cool, but only the first part in extracting a ML model for usage. The second part is reverse engineering the tokenizer and input transformations that are needed to before passing the data to the model, and outputting a human readable format.

This is a good comment, but only in the sense it documents a model file doesn't run the model by itself.

An analogous situation is seeing a blog that purports to "show you code", and the code returns an object, and commenting "This is cool, but doesn't show you how to turn a function return value into a human readable format" More noise, than signal.

The techniques in the article are trivially understood to also apply to discovering the input tokenization format, and Netron shows you the types of inputs and outputs.

Thanks for the article OP, really fascinating.

Re: Extracting AI models from mobile apps

#148

Post by frogsRnice »

avg_dev wrote: post #32

pretty cool; that frida tool seems really nice. https://frida.re/docs/home/ (and a bunch of people seem to be interested in the "IP" note, but I took as, just trying to not get run into legal trouble for advertising "here's how you can 'steal' models!")

frida is an amazing tool - it has empowered me to do things that would have otherwise took weeks or even months. This video is a little old, but the creator is also cracked https://www.youtube.com/watch?v=CLpW1tZCblo

It's supposed to be "free-IDA" and the work put in by the developers and maintainers is truly phenomenal.

EDIT: This isn't really an attack imo. If you are going to take "secrets" and shove it into a mobile app, they can't really be considered secret. I suppose it's a tradeoff - if you want to do this kind of thing client-side - the secret sauce isn't so secret.

Re: Extracting AI models from mobile apps

#149

Post by benreesman »

Ekaros wrote: post #146

Can you launder AI model by feeding it to some other model or training process? After all that is how it was originally created. So it cannot be any less legal...

There are a family of techniques, often called something like “distillation”. There are also various synthetic training data strategies, it’s a very active area of research.

As for the copyright treatment? As far as I know it’s a bit up in the air at the moment. I suspect that the major frontier vendors would mostly contend that training data is fair use but weights are copyrighted. But that’s because they’re bad people.

Re: Extracting AI models from mobile apps

#150

Post by qup »

benreesman wrote: post #149
Ekaros wrote: post #146

Can you launder AI model by feeding it to some other model or training process? After all that is how it was originally created. So it cannot be any less legal...

There are a family of techniques, often called something like “distillation”. There are also various synthetic training data strategies, it’s a very active area of research. As for the copyright treatment? As far as I know it’s a bit up in the air at the moment. I suspect that the major frontier vendors would mostly contend that training data is fair use but weights are copyrighted. But that’s because they’re bad peo…

The weights are my training data. I scraped them from the internet
Post reply on HN