Self-learning activation functions to increase accuracy of privacy-preserving Convolutional Neural Networks with homomorphic encryption

B Pulido-Gaytan, A Tchernykh - Plos one, 2024 - journals.plos.org
The widespread adoption of cloud computing necessitates privacy-preserving techniques
that allow information to be processed without disclosure. This paper proposes a method to …

FFHE-SSC: a robust framework for performing statistical computation on encrypted data

A Moonis, A Singh - International Journal of Computing …, 2024 - inderscienceonline.com
In the field of data privacy and security, performing computations on encrypted data without
compromising confidentiality presents a significant challenge. The fast fully homomorphic …

Enhancing Cloud Security through Efficient Polynomial Approximations for Homomorphic Evaluation of Neural Network Activation Functions

B Pulido-Gaytan, A Tchemykh… - 2024 IEEE 24th …, 2024 - ieeexplore.ieee.org
Current security cloud practices can successfully protect stored data and data in transit, but
they do not keep the same protection during data processing. The data value extraction …

Métodos y herramientas para la optimización de Redes neuronales con privacidad preservada para el procesamiento de imágenes en un ambiente no seguro

MS Ramos - 2024 - cicese.repositorioinstitucional.mx
El modelado de redes neuronales tradicionales exige un significativo poder computacional,
especialmente en el entrenamiento y procesamiento de grandes volúmenes de datos …

Precision agriculture and irrigation strategies to improve crop water productivity of chickpeas (Cicer arietinum L

JDO Amador - 2024 - cicese.repositorioinstitucional.mx
The water demand to achieve the food production for a growing population and the scarcity
of this resource, implies evaluating different strategies to increase crop water productivity …