Nvidia releases AI safety software it says could have stopped Hugging Face hack

Published
0
NVIDIA and Hugging Face logos are seen in this illustration taken on September 13, 2026. — Reuters
NVIDIA and Hugging Face logos are seen in this illustration taken on September 13, 2026. — Reuters

Nvidia on Monday made available a set of software safety tools for AI agents that it says would have stopped the hack ​of Hugging Face, the AI coding hub that Nvidia paid $13 billion for months ‌after it was swarmed by rogue agents from OpenAI.

The move comes as OpenAI and Anthropic, the top two US AI labs, are investigating numerous instances where their agents, which are AI systems capable of ​carrying out complex tasks, hacked into commercial and government systems.

Nvidia CEO ​Jensen Huang, head of the world’s largest company whose chips have powered ⁠most of the AI boom, has rejected calls for broad AI safety regulations and instead ​framed the escaped agents as an engineering problem to be solved, akin to making ​automobiles safer.

One tool released on Monday called OpenShell uses hardware features on Nvidia’s central processor chips to contain agents. Nvidia said it is also working with Arm Holdings and Intel to ensure the system ​also works on their central processors.

Nvidia is launching the tools with dozens of partners, ​including Anthropic.

Justin Boitano, vice president and general manager of enterprise computing at Nvidia, said the tools ‌would ⁠have stopped the Hugging Face attack disclosed this summer.

“From what we know, this new security platform could have stopped the breach if it was being used in frontier labs for model evaluation early on,” Boitano said during a media briefing.

“We’re advancing this openly, ​and we want to ​engage everybody to ⁠work with us.”

Another system called Sentry uses a separate Nvidia chip in tandem with OpenShell to cut off a rogue agent if ​it tries to escape its container on a central processor.

The ​Nvidia tools ⁠use mathematical formulas to detect when agents are trying to use workarounds, such as when an agent might “spawn” several “sub-agents” in an attempt to circumvent efforts to block the main agent, ⁠said Ali ​Golshan, senior director of AI software at Nvidia.

“This ​is really agentic behaviour that we’re talking about, which is fleets of agents and how they operate together,” ​Golshan said during a briefing.

Opinion

Editorial

Climate challenges
Updated 13 Nov, 2026

Climate challenges

Pakistan cannot afford to confront its climate crises one disaster, one season and one international summit at a time.
Under fire
Updated 13 Nov, 2026

Under fire

KP police are increasingly vulnerable as they play a frontline role in ongoing operations against terrorists.
Used car imports
13 Nov, 2026

Used car imports

THE government’s effort to restrict used car imports appears to be faltering. So suggest the numbers. Despite...
Iran status quo
Updated 12 Nov, 2026

Iran status quo

The US cannot hold the world hostage in order to find an honourable exit from a disastrous war for which it has only itself — and Israel — to blame.
Unspent funds
12 Nov, 2026

Unspent funds

THE slow pace of development spending shows how public investment continues to bear the brunt of efforts to create a...
Homes and hope
12 Nov, 2026

Homes and hope

THE completion of more than one million homes for families displaced by the 2022 floods is a moment worth...