12 Feb 2024

Advai enlisted to teach Army Adversarial AI

Army Cyber Association, British Army

Words by
Alex Carruthers
Categories
Partnerships Mentions
British Army Logo Vector

With excitement we can report that Advai were examiners in the Defence Cyber Marvel 2024 competition, organised by the Army Cyber Association. 

The Defence Cyber Marvel competition prepares armed forces for the future battleground of cyber warfare. This unique training competition was hosted by the UK for the third time, with over 1000 participants from across Defence, Government and international partners, including Met Police, DWP, DE&S, NCA, Republic of Korea Armed Forces, US Army, Japanese Defence Force, Indian Army, Defence Forces of Georgia, Philippine Army and many more.

The exercises were designed to challenge personnel to defend against real-world cyber threats.

This year's scenario involved analysis of AI models found on an enemy laptop and how to thwart AI-enabled threats. Focussing on disrupting an Object Detection model, participants were taught innovative methods for both preventing and provoking AI failure. The exercise highlighted the critical role that both AI and counter-AI will play in future warfare.

David Sully, Advai’s CEO commented, “whilst our regular business is to work with customers on mitigating AI failure or defending against Adversarial Attacks, the team enjoyed sitting on the other side of the fence for a change.”

Capt. Kirtley, one of DCM’s organiser, comments: “Advai’s expertise enabled everybody to walk away with critical knowledge about the role of Adversarial AI to capitalise on the vulnerabilities of an AI model, to protect ourselves from our adversaries’ capabilities whilst improving the security of our own systems.”

Who are Advai?

Established in 2020, Advai is a leading UK Deep Tech specialist focussed on AI Safety and Security. We test and evaluate Artificial Intelligence and Machine Learning systems, enabling our customers to assure their Large Language Models, Computer Vision and other AI-enabled technologies for deployment in business-critical or regulated environments. 

Our tooling stress-tests, measures and improves AI robustness and real world performance, finding reliable operating boundaries and creating early warning systems to predict natural or adversarial issues. As one of the most successful companies to have come through the Defence and Security Accelerator, we work with both the UK Ministry of Defence and a range of safety-conscious enterprises.

Advai is a proud partner of the UK Government’s Frontier AI Taskforce, the research unit behind the world's first global AI Safety Summit.

If you would like to discuss this in more detail, please reach out to contact@advai.co.uk