View source for 18488497. APPARATUS AND METHOD WITH ENCRYPTED DATA NEURAL NETWORK OPERATION simplified abstract (SEOUL NATIONAL UNIVERSITY R&DB FOUNDATION)

=APPARATUS AND METHOD WITH ENCRYPTED DATA NEURAL NETWORK OPERATION=


==Organization Name==

[[:Category:SEOUL NATIONAL UNIVERSITY R&DB FOUNDATION|SEOUL NATIONAL UNIVERSITY R&DB FOUNDATION]]


[[Category:SEOUL NATIONAL UNIVERSITY R&DB FOUNDATION]]

==Inventor(s)==

[[:Category:Jong-Seon No of Seoul (KR)|Jong-Seon No of Seoul (KR)]][[Category:Jong-Seon No of Seoul (KR)]]

[[:Category:Junghyun Lee of Seoul (KR)|Junghyun Lee of Seoul (KR)]][[Category:Junghyun Lee of Seoul (KR)]]

[[:Category:Yongjune Kim of Daegu (KR)|Yongjune Kim of Daegu (KR)]][[Category:Yongjune Kim of Daegu (KR)]]

[[:Category:Joon-Woo Lee of Seoul (KR)|Joon-Woo Lee of Seoul (KR)]][[Category:Joon-Woo Lee of Seoul (KR)]]

[[:Category:Young Sik Kim of Gwangju (KR)|Young Sik Kim of Gwangju (KR)]][[Category:Young Sik Kim of Gwangju (KR)]]

[[:Category:Eunsang Lee of Seoul (KR)|Eunsang Lee of Seoul (KR)]][[Category:Eunsang Lee of Seoul (KR)]]

==APPARATUS AND METHOD WITH ENCRYPTED DATA NEURAL NETWORK OPERATION - A simplified explanation of the abstract==


This abstract first appeared for US patent application 18488497 titled 'APPARATUS AND METHOD WITH ENCRYPTED DATA NEURAL NETWORK OPERATION

==Simplified Explanation==
The patent application describes an apparatus and method for operating a neural network with encrypted data. The apparatus generates a target approximate polynomial to approximate a portion of a neural network model.

* One or more processors execute instructions to generate the target approximate polynomial.
* The target approximate polynomial is based on a first approximate polynomial, input data parameters, and a target approximation region.
* The neural network operation result is generated using the target approximate polynomial and the input data.

==Key Features and Innovation==
* Apparatus and method for operating a neural network with encrypted data.
* Generation of a target approximate polynomial to approximate a portion of a neural network model.
* Utilization of input data parameters and a target approximation region to generate the target approximate polynomial.

==Potential Applications==
The technology can be applied in various fields such as cybersecurity, data encryption, and secure neural network operations.

==Problems Solved==
* Secure operation of neural networks with encrypted data.
* Efficient approximation of neural network operations.
* Protection of sensitive data during neural network processing.

==Benefits==
* Enhanced security for neural network operations.
* Improved efficiency in approximating neural network functions.
* Protection of sensitive data during computation.

==Commercial Applications==
Title: Secure Neural Network Operation with Encrypted Data
This technology can be utilized in industries such as cybersecurity, finance, healthcare, and defense for secure and efficient neural network operations with encrypted data.

==Prior Art==
Readers can explore prior research on encrypted neural network operations, secure data processing, and efficient approximation techniques in neural networks.

==Frequently Updated Research==
Stay updated on advancements in encrypted neural network operations, secure data processing, and efficient approximation methods for neural networks.

==Questions about Secure Neural Network Operation with Encrypted Data==
===How does the technology ensure the security of neural network operations with encrypted data?===
The technology utilizes encrypted data and a target approximate polynomial to securely operate neural networks while protecting sensitive information.

===What are the potential applications of this technology in different industries?===
This technology can be applied in cybersecurity, finance, healthcare, and defense sectors for secure and efficient neural network operations with encrypted data.


==Original Abstract Submitted==

An apparatus and method with encrypted data neural network operation is provided. The apparatus includes one or more processors configured to execute instructions and one or more memories storing the instructions, wherein the execution of the instructions by the one or more processors configures the one or more processors to generate a target approximate polynomial, approximating a neural network operation, of a portion of a neural network model, using a determined target approximation region, for the target approximate polynomial, based on a first approximate polynomial generated based on parameters corresponding to a generation of the first approximate polynomial, a maximum value of input data to the portion of the neural network layer, and a minimum value of the input data, and generate a neural network operation result using the target approximate polynomial and the input data.



[[Category:G06N3/048]]
[[Category:G06N3/08]]
[[Category:CPC_G06N3/048]]