SECURED INPUT DATA CLASSIFICATION METHOD USING A NEURAL NETWORK WITH CONVOLUTION
DE602019071203T2Active Publication Date: 2025-06-18IDEMIA PUBLIC SECURITY FRANCE
View PDF 0 Cites 0 Cited by
Patent Information
- Application Number
- DE602019071203
- Authority / Receiving Office
- DE · DE
- Patent Type
- Patents
- Current Assignee / Owner
- Priority Date
- 2018-10-04
- Filing Date
- 2019-10-02
- Publication Date
- 2025-06-18
- Estimated Expiration
- 2039-10-02
AI Technical Summary
Technical Problem
Existing biometric classification systems using convolutional neural networks (CNNs) face challenges in securely sharing and classifying confidential biometric data across entities without compromising data privacy.
Method used
A method for securely classifying input biometric data using a CNN involves determining a first classification vector and constructing a second classification vector with a non-zero reference distance, ensuring differential privacy and protecting confidential data.
Benefits of technology
The method effectively secures biometric data classification by generating a noisy classification vector that maintains reliability while minimizing the risk of compromising confidential databases.
✦ Generated by Eureka AI based on patent content.
Need to check novelty before this filing date? Find Prior Art
No text content released.