Technology offers more effective analysis of machine learning models than statistical testing, delivering safer, more resilient models; opens early access program
London, UK – Feb. 20, 2025 – Safe Intelligence, a pioneer in deep validation artificial intelligence (AI) systems, today announced that it has secured £4.15M in seed funding in an investment round led by Amadeus Capital Partners, with participation from new investor OTB Ventures and existing investor Vsquared Ventures.
A spin out from Imperial College London, Safe Intelligence provides a new way to carry out deep validation of AI models, allowing users to detect fragilities that could cause critical failures at run time. The Safe Intelligence solution then applies “robustification” processes to smooth out flaws, making models much more resilient in real-world deployments.
The need for this solution is urgent as the ability to build AI models has rapidly outstripped the capability to determine whether they will operate robustly when used in production. The more sophisticated a model is, the more unpredictable its output, and the greater the risk it contains fragilities that can cause operational failures. This creates extreme challenges in high safety domains such as finance, mobility, robotics, and aviation where model errors can cause significant losses or severe damage. A model’s performance may also need to be checked for fairness or other industry-specific operational benchmarks.
There are a wide range of ways in which Safe Intelligence helps across sectors. In financial services, for example, models routinely make high-stakes risk analyses to support lending decisions. However, the more sophisticated the models become, the higher the risk that unexpected combinations of inputs by applicants could swing the model’s results, potentially allowing widespread issues with inappropriate lending decisions. Safe Intelligence makes it possible to verify that cases would resolve correctly even in the face of such input variance. The solution gives users the ability to build up their own library of input disturbances and discover new ones.
The company offers command line tools and a platform for formal verification and robustification at scale. The solutions apply to a wide range of neural network and decision tree models in vision and tabular data. Some of these techniques will also apply to language models at a later stage.
Safe Intelligence also announced today that it has opened an early access program for companies in these high safety industries to address their validation challenges. The program provides access to tools, model validation and hands on support.
Safe Intelligence was founded by CTO Alessio Lomuscio, RAEng chair in Emerging Technologies and Professor of Safe Artificial Intelligence at Imperial College London. Over the past 25 years, he has co-authored more than 200 research papers and holds many patents on AI and its safety, attracting direct funding from the US, the UK, the EU, and private companies. He is a distinguished ACM member and a fellow of EurAI.
Newly appointed CEO Steven Willmott previously led product and engineering for the company. Prior to Safe Intelligence, he was the founder and CEO of 3scale, which became one of the leading API management infrastructure companies (acquired by Red Hat). He holds a Ph.D. in AI and co-led research for one of the leading AI labs in Europe at UPC in Barcelona, Spain.
“Safe Intelligence offers deep analysis of machine learning models enabling users to gain actionable insights that can make the model more robust,” said Alessio Lomuscio, CTO of Safe Intelligence. “Today we have reliable hardware and very dependable software. We want to help society use robust AI as well.”
Steven comments: “Existing software development is based on a foundation of unit testing all system components. As these components become machine learning based, we can no longer be completely sure of their behaviour and, hence, the systems we build. Our mission is to provide tools to radically improve our ability to validate machine learned components and get back to a world where we can have high confidence in our systems.”
Dr Manjari Chandran-Ramesh, Partner, Amadeus Capital Partners, adds: “As one of the earliest investors in AI, Amadeus sees that the potential of this enabling technology will only be fully realised if models can be relied on to perform. Banks, insurers and other corporates using complex AI models internally are holding back from applying them to frontline, customer-facing or regulated activity because of fears that their models are not robust enough. Safe Intelligence can identify fragilities, tackle them, and unleash the power of AI across industries from transport to finance.”
About Safe Intelligence
Safe Intelligence, an Imperial College London spin-off company, offers deep validation of machine learning models based on formal verification and robustification in a way that scales. Though AI is changing the world, ML models remain inherently fragile, cost millions in testing and pre-deployment failures, and advanced models can still be unusable due to risk. Safe Intelligence has unlocked the potential to verify, validate and robustify ML models using novel algorithmic methods, and building model libraries with patent pending tech, world class science, and enterprise software experience. At Safe Intelligence we are building the foundation for truly safe AI. Solutions are available across a range of domains including finance, aviation, mobility, and robotics. Visit us at safeintelligence.ai to join the early user program and get hands-on support for model analysis.
About Amadeus Capital Partners
A trailblazer for three decades, we invest in people who create transformational technologies and sustainable businesses. We back early stage and growth companies from our locations in Cambridge, London, Oxford, and San Francisco, and with our DACH partners Apex Ventures. Find out more here and follow us on LinkedIn and X.
About OTB Ventures
OTB Ventures is a pan-European deep tech VC fund specializing in Series A and late seed rounds. Its focus lies in supporting startups that pioneer unique technologies across four key verticals: Enterprise AI & Automation, SpaceTech, FinTech Infrastructure, and Cybersecurity. Established in 2017, OTB Ventures currently manages over €350 million on behalf of private and institutional investors, including the European Investment Fund, and has offices in Amsterdam, the Netherlands, and Warsaw, Poland. To find out more, visit our website and follow us on LinkedIn.
About Vsquared Ventures
Vsquared Ventures backs bold entrepreneurs engineering groundbreaking technologies addressing some of the world’s most pressing challenges to become global leaders. Investing in deep tech companies, Vsquared Ventures focuses on new space, new computing, energy transition, robotics and manufacturing, new computing and sensing, AI and next-gen software and tech-bio. Vsquared Ventures has built one of Europe’s strongest deep tech portfolios, including industry disruptors Isar Aerospace, IQM Quantum Computing, Zama.ai, Customcells, Neura Robotics and The Exploration Company. www.vsquared.vc
About Imperial College London
We are Imperial – a world-leading university for science, technology, engineering, medicine and business (STEMB), where scientific imagination leads to world-changing impact. As a global top ten university in London, we use science to try to understand more of the universe and improve the lives of more people in it. Across our nine campuses and throughout our Imperial Global network, our 22,000 students, 8,000 staff, and partners work together on scientific discovery, innovation and entrepreneurship. Their work navigates some of the world’s toughest challenges in global health, climate change, AI, business leadership and more. Founded in 1907, Imperial’s future builds on a distinguished past, having pioneered penicillin, holography and fibre optics. Today, Imperial combines exceptional teaching, world-class facilities and a habit of interdisciplinary practice to unlock scientific imagination.
