SERVER ELECTRONIC APPARATUS FOR ENHANCING SECURITY OF NEURAL NETWORK MODEL AND TRAINING DATA AND CONTROL METHOD THEREOF

• Main Authors: SHIN JUN BUM, LEE SEE WOO, KIM JUNG WOO
• Format: Patent
• Language: English; Korean
• Published: 14.05.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC COMMUNICATION TECHNIQUE; ELECTRICITY; PHYSICS; TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION

서버가 개시된다. 본 서버는 통신 인터페이스, 적어도 하나의 인스트럭션(instruction)이 저장된 메모리 및 통신 인터페이스 및 메모리와 연결되어 서버를 제어하는 프로세서를 포함하고, 프로세서는, 적어도 하나의 인스트럭션을 실행함으로써, 통신 인터페이스를 통해, 학습 데이터가 동형 암호화된 동형 암호문을 전자 장치로부터 수신하고, 동형 암호문에 기초하여 메모리에 저장된 제1 신경망 모델을 학습하여 제2 신경망 모델을 획득하고, 제2 신경망 모델에 랜덤값을 덧셈 연산하여 제3 신경망 모델을 획득하고, 제3 신경망 모델을 전자 장치로 전송하도록 통신 인터페이스를 제어하고, 통신 인터페이스를 통해, 제3 신경망 모델이 복호화된 제4 신경망 모델을 전자 장치로부터 수신하고, 제4 신경망 모델에 랜덤값을 뺄셈 연산하여 최종 신경망 모델을 획득할 수 있다. A server is disclosed. The server includes a communication interface, a memory configured to store at least one instruction, and a processor configured to be connected with the communication interface and the memory, and control the server, wherein the processor is configured to, by executing the at least one instruction, receive, through the communication interface, a homomorphic encryption wherein training data is homomorphically encrypted from an electronic apparatus, train a first neural network model stored in the memory based on the homomorphic encryption and acquire a second neural network model, perform an addition operation of a random value to the second neural network model and acquire a third neural network model, control the communication interface to transmit the third neural network model to the electronic apparatus, receive, through the communication interface, a fourth neural network model which is decrypted from the third neural network model from the electronic apparatus, and perform a subtraction operation of the random value to the fourth neural network model and acquire a final neural network model.