ARCHIVE
AI Security Threat Series:...
The threat hiding inside a model that passes every test A model that behaves perfectly in testing and perfectly in ...
ISO 42001: The AI Management...
ISO 42001 is showing up in procurement requirements. Enterprise customers are asking for it. NHS supply chain ...
AI Security Threat Series:...
Cloning a proprietary AI through its own front door Building a world-class AI model takes months of work, millions in ...
AI Security Threat Series:...
Proving your data was used to train an AI — without ever seeing it You do not need to extract someone's data from a ...
Building Resilient AI Agents:...
As AI agents become increasingly embedded within enterprise workflows, prompt injection attacks have emerged as a ...
MHRA SaMD Classification for...
I have spent the better part of a decade navigating the intersection of cybersecurity and regulated industries, from ...
AI Security Threat Series:...
Corrupting an AI before it ever goes live Most AI attacks happen at the point of use. Data poisoning happens much ...
NHS Clinical Safety and AI...
I've spent the better part of a decade in cybersecurity, working with digital health organisations and later across the ...