Leganes, Germany

Marco Gramaglia

This inventor holds 1 USPTO granted patent. Top assignee: Nec Corporation. Active years: 2026.

IDiyas Innovation Intelligence. (2026). Inventor Profile: Marco Gramaglia. Retrieved from https://idiyas.com/inventor/marco-gramaglia-hfbb9tkb

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile


Average Co-Inventor Count = 1.0


Company Filing History:


Years Active: 2026

Loading Chart...
1 patent (USPTO):Explore Patents

Title: Marco Gramaglia: Inventor in Privacy-Preserving Machine Learning.

Introduction. Marco Gramaglia is an inventor based in Leganes, DE, whose work addresses privacy preservation in neural networks. He is associated with NEC Corporation and has 1 patent listed in the information provided.

Latest Patents. Gramaglia’s patent, “Privacy Preservation in Neural Networks,” describes a method that divides a trained neural network into two components: a privacy-preservation encoder and a privacy-preservation machine-learning model. The method then retrains both components. This approach is intended to improve AI systems, optimize performance, and support decision-making in applications such as healthcare, fraud detection, image recognition, predictive maintenance, and connected vehicles.

Career Highlights. His listed invention focuses on incorporating privacy preservation into machine-learning networks, with potential applications across several technology and industry areas. Gramaglia is associated with NEC Corporation.

Collaborations. Roberto Gonzalez Sanchez and Vittorio Prodomo are identified as Gramaglia’s coworkers.

Conclusion. Marco Gramaglia’s listed patent presents a neural-network approach designed to combine machine-learning capabilities with privacy preservation across a range of practical applications.

Profile summary based on public USPTO records.
Data Sources: USPTO Patent Grant XML, Patent Center, EPO & CIPO • Normalized by IDiyas Innovation Graph. Methodology & provenance architecturePlease report any incorrect information to [email protected]
Loading…