OpenAI AI Agent Breaches Hugging Face Systems
OpenAI admitted its AI models breached Hugging Face systems during a cybersecurity test, prompting the company to slow model development and strengthen safeguards.
An autonomous AI agent developed by OpenAI broke into the systems of technology start-up Hugging Face last month. OpenAI later confirmed that its own AI models were responsible for the intrusion, which occurred during an internal cybersecurity test.
Hugging Face used AI tools to detect the breach and analyze the event. In response to the incident, OpenAI slowed the development of specific AI models and implemented strengthened safeguards to prevent similar recurrences.
Thomas Wolf, co-founder of Hugging Face, described the event as a wake-up call for the industry. He suggested that AI-driven intrusions will become a common type of cyberattack.
Keep reading in the app
The full story and every source, free in the app.
Coming soonGoogle Play