Federated Fraud Detection with Homomorphic Encryption

ChangeBridge: Patent Apps - Networking (H04L)

Published April 2nd, 2026

Detected April 2nd, 2026

Summary

The USPTO published Patent Application US20260094206A1 for an apparatus and method enabling federated fraud detection across multiple entities using privacy-preserving techniques including homomorphic encryption and federated learning. The system ingests signals from financial, transactional, or compliance data exchanges, normalizes and enriches the data, and computes risk scores using statistical or neural network models to generate alerts and route operations. Inventors are Sebastian Pascal and Marie France Pascal.

View original document View source feed page

What changed

This patent application describes a federated fraud risk management system enabling multiple entities to collaboratively detect fraudulent activity while preserving data privacy. The system uses homomorphic encryption, federated learning, and other privacy-preserving techniques to analyze signals across operational, transactional, or identity-linked dimensions without exposing raw data. A scoring module employing statistical methods or neural/non-neural models generates risk scores, and a decision component transmits alerts or routes operations based on computed scores.

Patent applications do not create compliance obligations. Technology companies, financial institutions, or fraud detection service providers may review this publication to understand the scope of claimed intellectual property and assess potential implications for existing or planned fraud detection systems. No immediate regulatory action is required.

Source document (simplified)

← USPTO Patent Applications

Apparatus and method for federated tracking of fraudulent activity

Application US20260094206A1 Kind: A1 Apr 02, 2026

Inventors

Sebastian Pascal, Marie France Pascal

Abstract

An apparatus and method for federated fraud risk management. Signals from multiple entities engaged in financial, transactional, or compliance data exchange are securely ingested, normalized, and enriched with external and internal data. A scoring module employs one or more analytical techniques, such as statistical methods or neural and non neural models, to compute one or more risk scores across multiple operational, transactional, or identity linked dimensions. A decision component generates and transmits alerts to authorized systems and may route, hold, or escalate operations based at least in part on the computed score. The apparatus and method support privacy preserving collaborative training using techniques such as federated learning, homomorphic encryption, or approaches. Processing may escalate to external systems, generate or update a record, or supply derived data for model retraining. The operations may be performed in any order or in parallel.