top of page

Home
EDDI
People
Blog
More

Use tab to navigate through the menu items.

Research Blog

Secure by Design in the AI Era: Why Trustworthy Products Start With Security Category: AI Security · Secure Software Engineering · Trustworthy Computing AI has changed what we build. Applications that once had a simple path from user interface to API to database now have large language models (LLMs), autonomous agents, vector databases, plug-in tools and third-party model APIs sitting in the middle. Each new component adds capability. Each one also adds attack surface. It is evident that in the AI era, security cannot be bolted on at the end. It has to be a core feature of the product from the first design decision. Let’s identify what a "secure product" is, why AI makes trustworthy computing both harder and more necessary, and some practical checklist that product teams can use. 1. What makes a product "secure"? Two sides of the CIA triad The centre focus of security is mostly described with the CIA triad: Confidentiality, Integrity and Availability.

Secure by Design in the AI Era: Why Trustworthy Products Start With Security Category: AI Security · Secure Software Engineering · Trustworthy Computing AI has changed what we build. Applications that once had a simple path from user interface to API to database now have large language models (LLMs), autonomous agents, vector databases, plug-in tools and third-party model APIs sitting in the middle. Each new component adds capability. Each one also adds attack surface. It is evident that in the AI era, security cannot be bolted on at the end. It has to be a core feature of the product from the first design decision. Let’s identify what a "secure product" is, why AI makes trustworthy computing both harder and more necessary, and some practical checklist that product teams can use. 1. What makes a product "secure"? Two sides of the CIA triad The centre focus of security is mostly described with the CIA triad: Confidentiality, Integrity and Availability.

Secure by Design in the AI Era: Why Trustworthy Products Start With Security

It is evident that in the AI era, security cannot be bolted on at the end. It must be a core feature from the first design decision. Let’s define what a "secure product" is, why AI makes trustworthy computing both harder and more necessary, and a practical checklist product teams can use.

1 day ago6 min read

Anthropic’s refusal to provide pre-release access exposes the risks of relying on privileged model access for frontier AI assessment.

Anthropic’s refusal to provide pre-release access exposes the risks of relying on privileged model access for frontier AI assessment.

When Frontier AI Goes Closed: Why AISI Needs Model-Agnostic Assurance

Anthropic’s refusal to provide pre-release access exposes the risks of relying on privileged model access for frontier AI assessment. Summary Anthropic’s decision not to provide Claude Mythos 5.1 to the UK AI Security Institute (AISI) for pre-release testing has been discussed mainly as a problem of voluntary cooperation, regulation and geopolitics. It is also a technical warning. Some of the strongest methods for understanding and controlling advanced models depend on priv

Sep 147 min read

+44 (0)1482 346311

Info@deis-hull.com

Cottingham Road, University of Hull

Hull, UK, HU6 7RX

Subscribe to Our Newsletter

Email

Thanks for submitting!

Follow Us On:

bottom of page