From SiliconANGLE · Paul Gillin · · 1m 20s
nFOX opens Blockhouse sandbox for open AI models
nFOX launches open-source AI security sandbox to protect enterprise models.
In brief
nFOX launches open-source AI security sandbox to protect enterprise models. nFOX will open-source Blockhouse, a Linux-based security sandbox that restricts AI model access to prevent breaches. Originally reported by SiliconANGLE.
nFOX launches Blockhouse
nFOX Lab today launched a platform for managing owned large language models and announced plans to open-source Blockhouse, a security sandbox designed to restrict what AI workloads can access and do.
Blockhouse security approach
Blockhouse removes privileges by default and lets administrators restore access deliberately through policies enforced at the linux kernel level.
Zero-trust security principles
The company’s approach borrows from zero-trust security principles by sharply limiting access and letting administrators restore privileges selectively.
Gordon Allott on AI security
Every model has the potential to be hostile, said Gordon Allott, nFOX’s founder and chief executive. We just presume hostility.
“Every model has the potential to be hostile”
Blockhouse operational details
Communications pass through Porthole, a monitored channel that allows requests to be reviewed before they are fulfilled. Runtime credentials and audit controls remain outside the model process.
Blockhouse security features
Blockhouse checks model integrity with sha-256 hashes and built-in checks halt serving if files change. It records containment events and reports when protection fails.
nFOX Platform availability
The nFOX Platform is available now. Blockhouse is available in beta test for qualified enterprise evaluations.
Here's the gist
nFOX will open-source Blockhouse, a Linux-based security sandbox that restricts AI model access to prevent breaches.
