- Published
- Source
- CSO Online UK
- Filed under
- Microsoft, UK industry, AI for defence
Microsoft and Nvidia are urging enterprises to assess the security of open-weight AI models throughout deployment, warning that changes to model weights and configurations can weaken safeguards even when a model retains its ability to perform assigned tasks. In a joint paper published last week, the companies identified 30 risk types across five categories and outlined a process for evaluating, mitigating, and monitoring them. The guidance calls for enterprises to verify model provenance, test the configurations they intend to deploy,…
Practical steps for any organisation
- Patch quickly, starting with anything facing the internet.
- Use multi-factor authentication everywhere it is offered.
- Keep tested, offline backups – and a plan for the day you need them.
More helpNCSC: 10 Steps to Cyber Security (opens in a new tab)NCSC: incident management (opens in a new tab)
MyCyberWay training
Microsoft SC-200 exam training
Defender and Sentinel in the headlines? That's the SC-200 toolkit.
Tutor-led SC-200 preparation: running security operations in Microsoft Sentinel and Defender XDR, responding to incidents across identity, endpoint, email and cloud, and threat hunting with KQL.
- Microsoft Sentinel and Defender XDR
- Incident response across Microsoft 365
- Threat hunting with KQL
Headlines and short summaries only, except where a public body publishes under an open licence. Every story links to its publisher, who owns it. MyCyberWay does not edit or endorse third-party reporting.
