Researchers Used AI to Breach OpenAI Systems
This story is only covered by news sources that have yet to be evaluated by the independent media monitoring agencies we use to assess the quality and reliability of news outlets on our platform. Learn more here.4 Articles
4 Articles
Researchers used Claude to hack OpenAI | #hacking | #cybersecurity | #infosec | #comptia | #pentest | #hacker - National Cyber Security Consulting
We’ve heard of OpenAI’s AI agents running amok and hacking other companies. Now, a cybersecurity company has turned the tables on the ChatGPT operator by using AI to help hack OpenAI itself. The hack, which also exposed a bug affecting dozens of other major online services, was conducted as security research. OpenAI paid the researchers […] Thank you for subscribing to our RSS feed!
Researchers Used AI to Breach OpenAI Systems
Cybersecurity researchers have warned that the artificial intelligence industry may not be sufficiently prepared for the security risks created by its own technologies, after a report revealed that a small team used Anthropic’s Claude chatbot to breach systems belonging to OpenAI.
The researchers of the Hacktron AI startup were able to access ChatGPT accounts linked to OpenAI employees during a security exercise carried out with the company's permission. To explore the vulnerability, the team used artificial intelligence models from Antropic, the main competitor of OpenAI. The test identified a failure in the OpenAI public aid forum, operated by the Discourse platform. Vulnerability allowed researchers to take control of …
Coverage Details
Bias Distribution
- There is no tracked Bias information for the sources covering this story.
Factuality
To view factuality data please Upgrade to Premium
