Privacy-preserving Learning via Deep Net Pruning
This addresses privacy concerns in machine learning for data-sensitive applications, offering a novel approach to differential privacy.
The paper investigates whether neural network pruning can achieve differential privacy while preserving data utility, proving that pruning a layer is equivalent to adding differentially private noise to activations and showing pruning can be more effective than adding noise in practice.
This paper attempts to answer the question whether neural network pruning can be used as a tool to achieve differential privacy without losing much data utility. As a first step towards understanding the relationship between neural network pruning and differential privacy, this paper proves that pruning a given layer of the neural network is equivalent to adding a certain amount of differentially private noise to its hidden-layer activations. The paper also presents experimental results to show the practical implications of the theoretical finding and the key parameter values in a simple practical setting. These results show that neural network pruning can be a more effective alternative to adding differentially private noise for neural networks.