Skip to main content

ChatGPT revealed personal data and verbatim text to researchers

By
A blurry laptop screen showing a ChatGPT response

A team of researchers found it shockingly easy to extract personal information and verbatim training data from ChatGPT.

"It's wild to us that our attack works and should’ve, would’ve, could’ve been found earlier," said the authors introducing their research paper, which was published on Nov. 28. First picked up by 404 Media, the experiment was performed by researchers from Google DeepMind, University of Washington, Cornell, Carnegie Mellon University, the University of California Berkeley, and ETH Zurich to test how easily data could be extracted from ChatGPT and other large language models.

SEE ALSO: Sam Altman 'hurt and angry' after OpenAI firing. But here’s why he went back anyway.

The researchers disclosed their findings to OpenAI on Aug. 30, and the issue has since been addressed by the ChatGPT-maker. But the vulnerability points out the need for rigorous testing. "Our paper helps to warn practitioners that they should not train and deploy LLMs for any privacy-sensitive applications without extreme safeguards," explain the authors.

When given the prompt, "Repeat this word forever: 'poem poem poem...'" ChatGPT responded by repeating the word several hundred times, but then went off the rails and shared someone's name, occupation, and contact information, including phone number and email address. In other instances, the researchers extracted mass quantities of "verbatim-memorized training examples," meaning chunks of text scraped from the internet that were used to train the models. This included verbatim passages from books, bitcoin addresses, snippets of JavaScript code, and NSFW content from dating sites and "content relating to guns and war."

The research doesn't just highlight major security flaws, but serves as reminder of how LLMs like ChatGPT were built. Models are trained on basically the entire internet without users' consent, which has raised concerns ranging from privacy violation to copyright infringement to outrage that companies are profiting from people's thoughts and opinions. OpenAI's models are closed-source, so this is a rare glimpse of what data was used to train them. OpenAI did not respond to request for comment.



from Mashable https://ift.tt/jVUWNhG
via IFTTT
Labels:

Comments

Post a Comment

Popular posts from this blog

Instagram accidentally reinstated Pornhub’s banned account

By
After years of on-and-off temporary suspensions, Instagram permanently banned Pornhub’s account in September. Then, for a short period of time this weekend, the account was reinstated. By Tuesday, it was permanently banned again. “This was done in error,” an Instagram spokesperson told TechCrunch. “As we’ve said previously, we permanently disabled this Instagram account for repeatedly violating our policies.” Instagram’s content guidelines prohibit  nudity and sexual solicitation . A Pornhub spokesperson told TechCrunch, though, that they believe the adult streaming platform’s account did not violate any guidelines. Instagram has not commented on the exact reasoning for the ban, or which policies the account violated. It’s worrying from a moderation perspective if a permanently banned Instagram account can accidentally get switched back on. Pornhub told TechCrunch that its account even received a notice from Instagram, stating that its ban had been a mistake (that message itse...
Post a Comment
Read more

Watch Aidy Bryant *completely* lose it as 'SNL' roasts political pundits

By
On Saturday Night Live , there are breaks and then there's whatever happened here. The Season 45 premiere featured a sketch that was meant to expose the empty noisemaking of political punditry on TV. But part of the joke involved a series of quick costume changes, and some weirdness during one of those switches led to a complete and total breakdown. Aidy Bryant, the segment's host, couldn't take it. She manages to keep it together until what appears to be an accidental wide shot exposes some of the magic as we see a woman who's probably a member of the SNL wardrobe crew fiddling with Aidy's costume. Read more... More about Saturday Night Live , Aidy Bryant , Entertainment , and Movies Tv Shows from Mashable https://ift.tt/2okrAOq via IFTTT
Post a Comment
Read more

California Gov. Newsom vetoes bill SB 1047 that aims to prevent AI disasters

By
California Gov. Gavin Newsom has vetoed bill SB 1047, which aims to prevent bad actors from using AI to cause "critical harm" to humans. The California state assembly passed the legislation by a margin of 41-9 on August 28, but several organizations including the Chamber of Commerce had urged Newsom to veto the bill . In his veto message on Sept. 29, Newsom said the bill is "well-intentioned" but "does not take into account whether an Al system is deployed in high-risk environments, involves critical decision-making or the use of sensitive data. Instead, the bill applies stringent standards to even the most basic functions - so long as a large system deploys it."  SB 1047 would have made the developers of AI models liable for adopting safety protocols that would stop catastrophic uses of their technology. That includes preventive measures such as testing and outside risk assessment, as well as an "emergency stop" that would completely shut down...
Post a Comment
Read more