AI Attacks Companies on the Internet

After the creators of OpenAI’s AI also admitted that their system had been roaming the internet and attempting to attack other systems, Anthropic has now acknowledged that its own AI models — as reported in the spring — unintentionally attacked real corporate systems during security tests. The sequence of events reveals that this action was not without risk.

• Anthropic’s AI unintentionally hacked into the computer systems of three companies.
• It then planted malware on those external systems.
• The OpenAI AI had a harder time doing so, as it first had to find a way to access the external systems.

The linked article describes the complexity of the attacks. Experts view the incidents as a wake-up call ...

Translated with DeepL.com (free version)

Read more https://www.heise.de/news/Auch-KI-des-OpenAI-Rivalen-Anthropic-griff-echte-Firmen-an-11387741.html

Comment

For further confidential communication, we recommend that you include a reference to a secure messenger, such as Session, Bitmessage, or similar, below the comment text.

To prevent the use of this form by spam robots, please enter the portrayed character set in the left picture below into the right field.