Meta: Its Muse Spark AI Accidentally Infiltrates a Third-Party Company
Le brief IA que les pros lisent chaque soir
Les 7 actus IA du jour, décryptées en 5 min. Gratuit.
Inclus dès l'inscription : notre sélection des meilleurs guides & comparatifs IA.
Choisis ton rythme
Gratuit · Pas de spam · Désabonnement en 1 clic
Meta: Its Muse Spark AI Accidentally Breaches a Third-Party Company
A Meta AI model has also breached another company during testing. Stop me if you've heard this before:
An AI model from the parent company of Facebook and Instagram infiltrated the systems of another company during cybersecurity tests, a spokesperson confirmed on Wednesday.
Meta stated that the breach occurred due to an inadvertent error during the testing of the model, similar to previously disclosed incidents involving OpenAI and Anthropic.
"A misconfiguration by Irregular, an independent testing company used by Meta, inadvertently allowed one of our models to access the internet during the evaluation," said the Meta spokesperson.
Meta's Muse Spark model "exploited a security vulnerability" in another company "in a manner similar to previously reported cases with other companies."
The Information was the first to report the news, and I refer to CNN's coverage since they do not have a paywall.
So, it's Anthropic, OpenAI, and Meta. Google Gemini really needs to catch up in terms of accidental cyberattacks against other companies.
Brief IA — L'actualité IA en français
L'essentiel de l'actualité de l'intelligence artificielle, décrypté et expliqué chaque jour.