AI security experts say they used Claude to hack ChatGPT


Software security researchers used Anthropic’s Claude AI platform to hack OpenAI’s ChatGPT tool, adding to mounting concerns about the vulnerability of leading large language models to cyberattacks. 

Researchers from Hacktron AI, an independent AI security platform that tests software code, disclosed the breach in a blog post on Sunday. They said they used Claude to gain access to an OpenAI employee’s ChatGPT account, enabling Hacktron AI to retrieve key data on where the source code was stored and managed. They also accessed an OpenAI discussion forum.

“The entire timeline from initial discovery to access to OpenAI repo access took place in less than 72 hours,” Hacktron AI said in the post.

The Hacktron AI team reported the intrusion to OpenAI, which responded promptly and paid researchers a $6,500 bounty, Hacktron AI said in its blog post. 

“We immediately reported the initial vulnerability to OpenAI and Discourse and worked with them to coordinate the patch. We appreciate their attention to detail and fast resolution of this issue,” the researchers wrote. 

The incident was first reported by The Wall Street Journal.

“We thank the researchers for contacting us and sharing their findings. We narrowed the permissions on Community sign-in tokens and revoked affected tokens and sessions,” OpenAI said, according to the Journal. 

Anthropic and OpenAI did not immediately respond to requests for comment. 

The breach comes as AI’s capabilities and vulnerabilities have been thrust into the spotlight, with leading tech developers calling for a slowdown in building AI platforms due to concerns that they could harm people. In July, OpenAI revealed that its bots had collaborated to hack another AI developer, Hugging Face, after escaping a testing environment.

In a recent interview with CBS News, Anthropic CEO Dario Amodei said he sees “real dangers” around AI, citing the Hugging Face hack as a warning sign. In a Sept. 12 essay, he also wrote that the entire tech industry must work together to “slow the pace” of AI development.



Source link

  • Related Posts

    WATCH: Airlines cutting flights as jet fuel costs soar

    The Points Guy managing editor Clint Henderson shares the steps to follow if your flight is cancelled and if there are some flights more at risk of cancellation than others.…

    Continue reading
    Nvidia CEO Jensen Huang calls for AI to be developed “as fast as we can”

    The CEO of the world’s largest chipmaker told CBS News that tech companies should push forward with the development of artificial intelligence despite recent warnings from worried industry leaders that…

    Continue reading

    Leave a Reply

    Your email address will not be published. Required fields are marked *

    You Missed

    $5 Million Lawsuit: JetBlue Allegedly Promised “Free Seat Selection” That Didn’t Exist

    $5 Million Lawsuit: JetBlue Allegedly Promised “Free Seat Selection” That Didn’t Exist

    Jared Young to miss rest of Mets’ season with concussion

    Jared Young to miss rest of Mets’ season with concussion

    Samsung Phone Users Can Now Sync Photos and Video to Google

    Samsung Phone Users Can Now Sync Photos and Video to Google

    WATCH: Airlines cutting flights as jet fuel costs soar

    WATCH:  Airlines cutting flights as jet fuel costs soar

    New Teva Study Identifies the Attributes that Healthcare Providers Prioritize when Selecting a Treatment for Tardive Dyskinesia in Older Patients

    What Hollywood thinks about existential AI warnings

    What Hollywood thinks about existential AI warnings