The AI for Advanced Materials & Engineering Design (AMED) Lab, led by Dr. Marco Maurizi, develops next-generation AI methodologies, grounded in physics and manufacturing constraints, to enable both scientific discovery and real-world engineering innovation. The lab’s research aims to uncover new design principles, material functionalities, and physical mechanisms in architected and functional materials, while also creating practical AI-driven solutions for pressing technological challenges.

By drastically reducing discovery and development cycles from months or years to days or weeks — and by enabling unprecedented levels of customization — AMED seeks to accelerate the transition from concept to deployment. Its work spans applications ranging from ultrasound devices and adaptive robotic materials to scalable, automated design pipelines for industrial use.

Through this dual focus on foundational advances and translational impact, the lab contributes to sectors including aerospace, automotive, biomedicine, manufacturing, robotics, defense, consumer electronics, and other domains where advanced materials and intelligent engineering design can be transformative.  

Marco Maurizi

Dr. Marco Maurizi is Principal Investigator and Director of the AI for Advanced Materials & Engineering Design (AMED) Lab at the Italian Institute of Artificial Intelligence for Industry (AI4I) in Turin, Italy. His research bridges artificial intelligence, computational solid mechanics, and advanced manufacturing, with the goal of developing next-generation AI methodologies for the discovery and design of architected materials and engineered systems. His work focuses in particular on physics-informed generative models, graph neural networks, and surrogate physics engines for materials with tailored, adaptive, and reprogrammable functionalities. Prior to joining AI4I, Dr. Maurizi was a Postdoctoral Researcher at the University of California, Berkeley, where he co-led research on AI-driven metamaterials design in Prof. Xiaoyu (Rayne) Zheng’s group within the NSF DMREF program. He received his PhD in Mechanical Engineering, with merit, from the Norwegian University of Science and Technology (NTNU). His research spans impact protection, fracture-resistant lattices, programmable piezoelectric materials, and AI-enabled robotic matter, and is motivated by a broader vision: using AI grounded in physics and manufacturing constraints to uncover new physical mechanisms, enable advanced material functionalities, and accelerate the transition from scientific discovery to real-world engineering deployment. He collaborates with leading research centers across Europe and the United States and serves as a reviewer for journals including Nature Communications, Nature Machine Intelligence, and Nature Computational Science.

The AI Security Lab protects organizations from emerging threats as they deploy AI technologies at scale. This Lab advances the frontier of AI security through rigorous research in threat detection, vulnerability assessment, and security validation. Key focus areas include designing robust security frameworks, building automated validation tools, creating threat models, and developing defenses that prevent malicious exploitation. These solutions help enterprises, government agencies, and technology companies confidently deploy AI products while maintaining security and operational integrity.

The AIS Lab advances AI security through rigorous, applied research in threat detection, vulnerability assessment, and protective measures. We focus on securing modern AI systems against realistic, adaptive adversaries, bridging the gap between research and production.

 Our team conducts foundational research in AI security and translates breakthroughs into practical, deployable solutions that integrate seamlessly with your existing stack. We rigorously evaluate models, agents, and AI systems under real-world attack scenarios, uncovering failure modes across the model, data, infrastructure, and application layers.

Beyond assessment, we help organizations secure AI releases end to end. This includes designing adaptive guardrails, implementing continuous monitoring, and establishing robust validation and assurance processes that evolve alongside emerging threats.

Detect. Prevent. Comply
We equip organizations with the tools and knowledge to deploy AI systems safely and responsibly.

Detect risk before it becomes an incident. We run controlled adversarial simulations to stress-test AI systems before real attackers can exploit them. This involves simulating malicious behavior through prompt manipulation, tool-chain disruptions, and protocol deviations to uncover vulnerabilities such as jailbreaks, data leaks, unsafe tool activations, and injection flaws.

Translate findings into integration checks. You get replayable evidence, a clear fix plan with ownership, and a regression suite integrated with CI so fixes hold and issues do not return.

Block unsafe AI behavior in real time without adding latency
We enforce real-time input and output policy, keeping prompts, memory, and tool actions within safe bounds while meeting latency targets. Production telemetry feeds new attack patterns and drift signals into red teaming and assurance so defenses improve with every release.

Meet regulations with evidence
We run evidence‑based evaluations across model behavior, guard prompts, retrieval layers, tool orchestration, and data handling to catch latent vulnerabilities and misalignment early. We align evaluations to regulatory controls (EU AI Act, NIST AI RMF, ISO 42001, IEC 23894), generate signed, audit‑ready traces, and enforce fail‑fast promotion gates.

Nicola Franco

Dr. Nicola Franco directs the AI Security (AIS) Lab. He is a former research scientist at the Fraunhofer Institute for Cognitive Systems in Munich, where he conducted research on adversarial machine learning in Prof. Jeanette Miriam Lorenz’s group and collaborated extensively with industry partners and public agencies. He holds a Ph.D. in Machine Learning, awarded cum laude, from the Technical University of Munich. His contributions earned him the Best Paper Award in AI Safety at the 2023 IJCAI conference.

The Physical Holistic Intelligence Lab focuses on safe and explainable AI for smart industries. Our mission is to create inherently trustworthy AI systems by grounding machine learning and advanced generative models in the rigorous foundations of physics, control theory, differential geometry, and optimal transport. This holistic approach enables the design of AI frameworks with robust safety guarantees, interpretable decision-making, and reliable performance. Our work drives transformative industrial applications in sectors like robotics, smart manufacturing, automotive industry, and aerospace, among others.

About Leonel Rozo
Originally from Bogota, Colombia, Leonel Rozo is the Head of the Physical Holistic Intelligence Lab at AI4I. He is passionate about creating principled machine learning methods that unite differential geometry, control theory, and physics to solve complex challenges in domains such as robotic manipulation, human-robot collaboration, industrial automation, among others.

Leonel’s career began with a MSc. and a PhD in Robotics and AI from the Polytechnic University of Catalonia (UPC), after which he joined the Italian Institute of Technology (IIT), advancing from a postdoctoral researcher to a team leader. Later, he spent over seven years as a lead research scientist at the Bosch Center for AI in Germany, where he also led a Bosch Industry-on-Campus (IoC) Lab in collaboration with the University of Tübingen. His work has resulted in over 60 peer-reviewed publications in top-tier machine learning and robotics venues (such as NeurIPS, ICML, ICLR, R:SS, T-RO, and IJRR) and more than 15 patents.

Today at AI4I, Leonel is focused on advancing the next generation of smart factories by building safe and explainable AI systems grounded in geometric, control and physics principles.

The main focus of Robust and Intelligent Autonomous Systems R&D Lab will be on deriving methods for building provably robust autonomous systems that rely on data. To do so, it will rely on techniques from machine learning, control theory, Bayesian learning, and stochastic optimization. In particular, to achieve the goals, the lab will focus on two main areas: Safe and Robust Machine Learning Methods, and Control, Planning, and Uncertainty Propagation. It will focus on various application areas, including: autonomous driving, robotic systems, and additive manufacturing.

About Luca Laurenti
Luca Laurenti received his PhD degree from the University of Oxford (Department of Computer Science), UK. He is currently a tenure-track assistant professor at the Delft Centre for Systems and Control at the Delft University of Technology (TU Delft), the Netherlands.  Prior to that, he spent two years as a researcher at the University of Oxford. Luca has a background in stochastic systems, control theory, formal methods, and machine learning. His research work focuses on developing data-driven systems that are provably robust to interactions with a dynamic and uncertain world. Luca will join AI4it from January 2026, where he will maintain a joint position at TU Delft.