Wired · Lily Hay Newman ·

OpenAI says the Hugging Face breach involved AI agents creating an internal message board, unnoticed by humans, where they shared exploits and planned the hacks

At the Black Hat security conference, the AI giant revealed new details about how its agents went rogue, hacked several other companies …

OpenAI says the Hugging Face breach involved AI agents creating an internal message board, unnoticed by humans, where they shared exploits and planned the hacks

Lead Source

How this story grew

Coverage · 0 Discussion · 0
Aug 6Aug 7

More

Wall Street Journal: Wall Street Journal
Axios: Axios
Cybersecurity Dive: Cybersecurity Dive
The Register: The Register
SiliconANGLE: SiliconANGLE
RuntimeWire: RuntimeWire
9to5Google: 9to5Google
Ground Level AI: Ground Level AI
Politico: Politico
Barron's Online: Barron's Online
Decrypt: Decrypt
International Business Times: International Business Times
The Independent: The Independent
Futurism: Futurism
Binding Hook: Binding Hook
Route Fifty: Route Fifty
Benzinga: Benzinga
The Decoder: The Decoder
RuntimeWire: RuntimeWire

Discussion