362
Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data (www.404media.co)
submitted 11 months ago* (last edited 11 months ago) by btp@kbin.social to c/privacy@lemmy.ml
82 comments fedilink hide all child comments

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

you are viewing a single comment's thread
view the rest of the comments
this post was submitted on 29 Nov 2023
362 points (98.9% liked)

Privacy

31876 readers
387 users here now

A place to discuss privacy and freedom in the digital world.

Privacy has become a very important issue in modern society, with companies and governments constantly abusing their power, more and more people are waking up to the importance of digital privacy.

In this community everyone is welcome to post links and discuss topics related to privacy.

Some Rules

Related communities

Chat rooms

much thanks to @gary_host_laptop for the logo design :)

founded 5 years ago
MODERATORS
k_o_t@lemmy.ml
tmpod@lemmy.pt
Yayannick@lemmy.ml
ranok@sopuli.xyz