08 Oct 2021

Presenting at a Seminar titled "Tricking AI – Perhaps It’s Not As Intelligent As You Think?"

City University of London

Words by
Alex Carruthers
Categories
Speaking
City University Of London

https://www.city.ac.uk/news-and-events/events/2021/10/tricking-ai-perhaps-its-not-as-intelligent-as-you-think

Advai is gearing up to present at an upcoming seminar, addressing some of the most pressing challenges in modern AI. As a forward-thinking UK startup, our mission is to pinpoint and remedy the vulnerabilities inherent in state-of-the-art AI systems, ensuring they are robust, secure, and fair from their very first deployment in the real world.

The seminar will delve into the increasingly prevalent association of AI with deep learning, a field known for its exceptional pattern recognition capabilities across various domains, including computer vision and natural language processing. Yet, these advancements are not without their challenges, particularly concerning explainability, data integrity, and robustness in out-of-sample scenarios.

One of the most critical vulnerabilities we'll discuss is Adversarial AI, where subtle input alterations can deceive neural networks—a threat to modern AI that is gaining attention from leading organisations such as Gartner, the Turing Institute, and Microsoft.

Our CEO, David Sully, brings his extensive experience from the Foreign Commonwealth Office and his expertise in international negotiations to the table. Alongside him, our Chief Researcher, Damian Ruck, will share insights from his pioneering work in AI Robustness and Security, underpinned by his academic background in computational social science and his experience tackling complex data science issues.

Join us as we explore these topics and share our journey in advancing the field of AI.

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