Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Kaplan, Caelin"'
As Internet of Things (IoT) technology advances, end devices like sensors and smartphones are progressively equipped with AI models tailored to their local memory and computational constraints. Local inference reduces communication costs and latency;
Externí odkaz:
http://arxiv.org/abs/2405.04249
Autor:
Kaplan, Caelin G., Xu, Chuan, Marfoq, Othmane, Neglia, Giovanni, de Oliveira, Anderson Santana
Within the realm of privacy-preserving machine learning, empirical privacy defenses have been proposed as a solution to achieve satisfactory levels of training data privacy without a significant drop in model utility. Most existing defenses against m
Externí odkaz:
http://arxiv.org/abs/2310.12112
Recent works have shown that selecting an optimal model architecture suited to the differential privacy setting is necessary to achieve the best possible utility for a given privacy budget using differentially private stochastic gradient descent (DP-
Externí odkaz:
http://arxiv.org/abs/2302.02910