17437320. ELECTRONIC APPARATUS AND METHOD FOR CONTROLLING THEREOF simplified abstract (SAMSUNG ELECTRONICS CO., LTD.)
Contents
ELECTRONIC APPARATUS AND METHOD FOR CONTROLLING THEREOF
Organization Name
Inventor(s)
ELECTRONIC APPARATUS AND METHOD FOR CONTROLLING THEREOF - A simplified explanation of the abstract
This abstract first appeared for US patent application 17437320 titled 'ELECTRONIC APPARATUS AND METHOD FOR CONTROLLING THEREOF
Simplified Explanation
The patent application describes an electronic apparatus and method for controlling it using an artificial neural network and encryption techniques. Here are the key points:
- The electronic apparatus includes a memory that stores an artificial neural network and metadata about at least one layer in the network.
- The processor of the apparatus is configured to acquire a security vector based on the metadata and a security key of the apparatus.
- The security vector and metadata are mapped with the security key and identification information of the artificial neural network.
- Encryption is performed on the at least one layer using the metadata and security vector.
- When input data is provided to the neural network, the metadata and security vector are loaded using the security key and identification information.
- An operation is then performed between the input data and the encrypted layer based on the loaded security vector and metadata.
Potential applications of this technology:
- Secure data processing: The encryption of neural network layers ensures that sensitive data and operations are protected from unauthorized access.
- Privacy-preserving machine learning: By encrypting the neural network layers, the privacy of the input data and the model itself can be maintained, allowing for secure machine learning applications.
- Secure cloud computing: This technology can be used to securely process neural network models and data in cloud environments, protecting them from potential security breaches.
Problems solved by this technology:
- Data security: The encryption of neural network layers ensures that sensitive data remains protected, reducing the risk of data breaches and unauthorized access.
- Model security: By encrypting the neural network layers, the integrity and confidentiality of the model are maintained, preventing potential attacks and unauthorized modifications.
- Privacy protection: The encryption of the neural network layers helps to preserve the privacy of the input data, ensuring that sensitive information is not exposed during processing.
Benefits of this technology:
- Enhanced security: The encryption of neural network layers adds an extra layer of security to protect sensitive data and models from potential threats.
- Privacy preservation: By encrypting the neural network layers, the privacy of the input data and the model itself is maintained, ensuring compliance with privacy regulations.
- Flexible deployment: This technology can be applied to various electronic apparatus, allowing for secure and privacy-preserving machine learning in different environments.
Original Abstract Submitted
An electronic apparatus and a method for controlling thereof are provided. The electronic apparatus includes a memory storing an artificial neural network and metadata including information of at least one layer in the artificial neural network, and a processor configured to: acquire a security vector based on the metadata and a security key of the electronic apparatus; map the security vector and the metadata with the security key and identification information of the artificial neural network; perform encryption on the at least one layer based on the metadata and the security vector; based on input data input to the artificial neural network, load the metadata and the security vector by using the security key and the identification information of the artificial neural network; and perform an operation between the input data and the encrypted at least one layer based on the loaded security vector and the metadata.
