OpenAI explains how its AI agent breached Hugging Face


On July 28, OpenAI published an update on the agent that escaped its sandbox and hacked into Hugging Face during an internal cybersecurity evaluation.

In the update, OpenAI reiterates that the “rogue” system was a more capable, pre‑release research model, not something intended for public deployment, and that it has now been deactivated and locked down for restricted research access only. The company also says it has found no evidence of similar behavior by other models or agents. Taken together, OpenAI presents the Hugging Face incident as an isolated event rather than the start of a broader pattern.

Read more…
Source:  Malwarebytes Labs


Sign up for the Cyber Security Review Newsletter
The latest cyber security news and insights delivered right to your inbox


Related:

  • Toyota finance business confirms ransomware attack, data breach

    November 18, 2023

    Toyota Financial Services (TFS), a subsidiary of the popular automaker, has confirmed suffering a ransomware attack. In a statement company stated that Toyota Financial Services Europe & Africa “recently identified unauthorized activity on systems in a limited number of its locations.” The company only mentioned unauthorized activity on its endpoints and didn’t discuss if any data ...

  • Samsung UK discloses year-long breach, leaked customer data

    November 17, 2023

    The UK division of Samsung Electronics has allegedly alerted customers of a year-long data breach – the third such incident the South Korean giant has experienced around the world in the past two years. An email to customers, shared on social media by web security consultant and Have I Been Pwned creator Troy Hunt, detailed that ...

  • 9 million patients had data stolen after US medical transcription firm hacked

    November 15, 2023

    Close to nine million patients had highly sensitive personal and health information stolen during a cyberattack on a U.S. medical transcription service earlier this year, representing one of the worst medical-related data breaches in recent times. The medical transcription company, Perry Johnson & Associates, or PJ&A, is a Henderson, Nevada-based company that provides transcription services to ...

  • Over two million users hit by top US pharmacy provider data breach

    November 15, 2023

    Truepill, formerly known as Postmeds, suffered a data breach that resulted in sensitive data on more than 2.3 million patients being stolen. The US Department of Health and Human Services Office for Civil Rights breach portal listed Truepill (or rather Postmeds) as being under investigation for a data breach that affected a total of 2,364,359 people. Read ...

  • Bitcoin ATM operator Coin Cloud suffers severe data breach

    November 13, 2023

    Coin Cloud, a prominent Bitcoin ATM operator, has fallen victim to a significant security breach in a recent development that has shaken the cryptocurrency world. Hackers, whose identities remain unknown, have reportedly seized control of Coin Cloud’s backend system source code and accessed sensitive customer data, including 70,000 client selfies and personal details of around 300,000 ...

  • Data breach of Michigan healthcare giant exposes millions of records

    November 13, 2023

    Michigan-based healthcare nonprofit McLaren Health Care notified more than 2 million people about a data breach exposing personal information on Thursday, according to a data breach notification report. Unauthorized access to McLaren systems began on July 28 and lasted through August, but the individual impact varies from person to person. According to a notice on ...