Skip to main content

Insights

When AI Can Be Fooled – Robust Models as the Goal of Modern AI Projects Insights

When AI Can Be Fooled – Robust Models as the Goal of Modern AI Projects

By Marvin Vogt, Fraunhofer FOKUS Whether it’s self-driving cars, malware detection, or text generation: neural networks have long since established themselves as a key technology for many innovative applications. However, it has become apparent that such machine learning systems are vulnerable to malicious actors. This article is intended to provide a…
Digital Twins-based Assurance-driven AI-empowered SecDevOps Insights

Digital Twins-based Assurance-driven AI-empowered SecDevOps

By Phu Nguyen and Adela Nedisan Videsjorden, SINTEF Digital systems today are more complex and critical than ever. They are built from many interconnected components, often combining third-party hardware and software. At the same time, rapid development cycles and evolving cyber threats—especially with Generative AI—make security increasingly difficult. SECASSURED envisions Digital…