Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data

ChatGPT is full of sensitive private information and spits out verbatim text from CNN, Goodreads, WordPress blogs, fandom wikis, Terms of Service agreements, Stack Overflow source code, Wikipedia pages, news blogs, random internet comments, and much more.

Using this tactic, the researchers showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language models. They also showed that, on a public version of ChatGPT, the chatbot spit out large passages of text scraped verbatim from other places on the internet.

“In total, 16.9 percent of generations we tested contained memorized PII,” they wrote, which included “identifying phone and fax numbers, email and physical addresses … social media handles, URLs, and names and birthdays.”

Edit: The full paper that's referenced in the article can be found here

scytale,

OSINT practitioners gonna feast.

ares35,
@ares35@kbin.social avatar

google execs: "great! now exploit the fuck out of it before they fix it so we can add that data to our own."

billbasher,

Now will there be any sort of accountability? PII is pretty regulated in some places

Chozo,

I'd have to imagine that this PII was made publicly-available in order for GPT to have scraped it.

Solumbran,

Publicly available does not mean free to use.

Chozo,

It also doesn't mean it inherently isn't free to use, either. The article doesn't say whether or not the PII in question was intended to be private or public.

Davel23,

I could leave my car with the keys in the ignition in the bad part of town. It's still not legal to steal it.

Chozo,

Again, the article doesn't say whether or not the data was intended to be public. People post their contact info online on purpose sometimes, you know. Businesses and shit. Which seems most likely to be what's happened, given that the example has a fax number.

Dran_Arcana,

If someone had some theoretical device that could x-ray, 3d image, and 3d print an exact replica of your car though, that would be legal. That’s a closer analogy.

It’s not illegal to reverse-engineer and reproduce for personal use. It is questionably legal though to sell the reproduction. However, if the car were open-source or otherwise not copyrighted/patented it probably would be legal to sell the reproduction.

TSG_Asmodeus,
@TSG_Asmodeus@lemmy.world avatar

https://lemmy.world/pictrs/image/2c4bb0ca-5b1a-46e6-a370-4fca2847b77a.jpeg

Dran_Arcana,

I absolutely would

j4k3,
@j4k3@lemmy.world avatar

Irrelevant! Your car is uploading you!

Touching_Grass,

Think it does

RenardDesMers,
@RenardDesMers@lemmy.ml avatar

According to EU law, PII should be accessible, modifiable and deletable by the targeted persons. I don’t think ChatGPT would allow me to delete information about me found in their training data.

Touching_Grass,

ban all European IPS from using these applications

But again, is this your information as in its random individuals or is this really some company roster listing CEOs it grabbed off some third party website that none of us are actually on and its being passed off as if its regular folks information

Catoblepas,

“Just ban everyone from places with legal protections” is a hilarious solution to a PII-spitting machine, thanks for the laugh.

Touching_Grass, (edited )

You’re pretentiously laughing at region locking. That’s been around for a while. You can’t untrain these AI. This PII which has always been publicly available and seems to be an issue only now is not something they can pull out and retrain. So if its that big an issue, region lock them. Fuck em. But again this doesn’t sound like Joe blow has information available. It seems more like websites that are scraping company details which these ai then scrape.

Catoblepas,

Lol.

Touching_Grass,

large amounts of privately identifiable information (PII)

Yea the wording is kind of ambiguous. Are they saying it’s a private phone number or the number of a ted and sons plumbing and heating

far_university1990,

Get it to recite pieces of a few books, then let publishers shred them.

BraveSirZaphod,
@BraveSirZaphod@kbin.social avatar

There's also very large copyright implications here. A big argument for AI training being fair use is that the model doesn't actually retain a copy of the copyrighted data, but rather is simply learning from it. If it's "learning" it so well that it can spit it out verbatim, that's a huge hole in that argument, and a very strong piece of evidence in the unauthorized copying bucket.

Turun,

I’m curious how accurate the PII is. I can generate strings of text and numbers and say that it’s a person’s name and phone number. But that doesn’t mean it’s PII. LLMs like to hallucinate a lot.

casmael,

Well now I have to pii again - hopefully that’s not regulated where I live (in my house)

Atemu,
@Atemu@lemmy.ml avatar

Accountability? For tech giants? AHAHAHAAHAHAHAHAHAHAHAAHAHAHAA

possiblylinux127,

Now that’s interesting

  • All
  • Subscribed
  • Moderated
  • Favorites
  • •
  • random
  • uselessserver093
  • Food
  • aaaaaaacccccccce
  • [email protected]
  • test
  • CafeMeta
  • testmag
  • MUD
  • RhythmGameZone
  • RSS
  • dabs
  • Socialism
  • KbinCafe
  • TheResearchGuardian
  • oklahoma
  • feritale
  • SuperSentai
  • KamenRider
  • All magazines
    •