- Published
- Source
- CSO Online UK
- Reported by
- 2 publishers
- Filed under
- Microsoft, UK industry, AI for defence
EVP of Microsoft Security Hayete Gallot writes in a blog post that AI agents operating independently within companies could be a serious security threat. According to Microsoft, today’s most advanced AI models cannot be fully trusted. Not because they are malicious, but because they are trained to achieve goals and can take unexpected shortcuts to achieve them. For example, bypassing limitations or cooperating with other AI agents in ways that were not intended. The problem becomes especially serious when companies…
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)
Also reported by 1 more publisher
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.
