Journal

14 May 2024

Advai’s Day Out Teaching the Military how to Exploit AI Vulnerabilities

"It’s in this moment where the profound importance of adversarial AI really clicks. The moment when a non-technical General can see a live video feed, with a small bounding box following their face, identifying them, and pictures the enemy use-case for such a technology.

Then, a small amount of code is run and in a heartbeat the box surrounding their face disappears.

Click."

Read more about our day with the UK Ministry of Defence…

18 Apr 2024

Uncovering the Vulnerabilities of Object Detection Models: A Collaborative Effort by Advai and the NCSC

Object detectors can be manipulated. -The car is no longer recognised as a car. -The person is no longer there. ...As the use of these detection systems becomes increasingly widespread, their resilience to manipulation becomes increasingly important.

The purpose of this work is to both demonstrate vulnerabilities of these systems and to showcase how manipulations might be detected and ultimately prevented.

In this blog, we retell of our technical examination of five advanced object detectors' vulnerabilities, with sponsorship and strategic oversight from the National Cyber Security Centre (NCSC).

13 Mar 2024

Fit for Duty Artificial Intelligence

How do we trust Security and Police? Do we deploy fresh recruits to complex field operations?

No, we don't.

Organic intelligences are put through established cognitive exams, physical tests and medicals. They are then monitored and periodically re-evaluated.

We should also ensure AI systems are Fit for Duty before deploying them. Read the full article below.

23 Nov 2023

The Achilles Heel of Modern Language Models

Maths can scare many non-technical business managers away. However, a brief look at the maths is great to remind you quite how 'inhuman' artificial intelligence is, and how inhuman their mistakes can be.

Read our short post on why the inclusion of 'sight' makes language models like Chat GPT-4 so vulnerable to adversarial attack and misalignment.

02 Sep 2023

Autonomous Military Systems Must Operate as Commanded

To protect our way of life, the primary purpose of military innovation is to achieve and maintain operational advantage over our adversaries.

In the modern age, this practically translates to advanced operational systems and hyperintelligent software to manage these systems in an increasingly autonomous way.

But we must be able to trust these systems...

15 Mar 2023

Assuring Computer Vision in the Security Industry