paper-with-me

홈 › Papers

Controlling the privacy loss with the input feature maps of the layers in convolutional neural networks

2018-05-09 · Woohyung Chun, Sung-Min Hong, Junho Huh, Inyup Kang

We propose the method to sanitize the privacy of the IFM(Input Feature Map)s that are fed into the layers of CNN(Convolutional Neural Network)s. The method introduces the degree of the sanitization that makes the application using a CNN be able to control the privacy loss represented as the ratio of the probabilistic accuracies for original IFM and sanitized IFM. For the sanitization of an IFM, the sample-and-hold based approximation scheme is devised to satisfy an application-specific degree of the sanitization. The scheme approximates an IFM by replacing all the samples in a window with the non-zero sample closest to the mean of the sampling window. It also removes the dependency on CNN configuration by unfolding multi-dimensional IFM tensors into one-dimensional streams to be approximated.

📄 PDF Abstract BibTeX arXiv:1805.03444

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Supervised Topological Maps

2020-08-14 · Francesco Mannella

Controlling the internal representation space of a neural network is a desirable feature because it allows to generate new data in a supervised manner. In this paper we will show how this can be achieved while building a…

Partial sensitivity analysis in differential privacy

2021-09-22 · Tamara T. Mueller, Alexander Ziller, Dmitrii Usynin, Moritz Knolle 외

Differential privacy (DP) allows the quantification of privacy loss when the data of individuals is subjected to algorithmic processing such as machine learning, as well as the provision of objective privacy guarantees. …

image-classificationImage ClassificationSensitivity

Differentially Private Over-the-Air Federated Learning Over MIMO Fading Channels

2023-06-19 · Hang Liu, Jia Yan, Ying-Jun Angela Zhang

Federated learning (FL) enables edge devices to collaboratively train machine learning models, with model communication replacing direct data uploading. While over-the-air model aggregation improves communication efficie…

Federated LearningPrivacy Preserving

Adversarial Learning of Privacy-Preserving and Task-Oriented Representations

2019-11-22 · Taihong Xiao, Yi-Hsuan Tsai, Kihyuk Sohn, Manmohan Chandraker 외

Data privacy has emerged as an important issue as data-driven deep learning has been an essential component of modern machine learning systems. For instance, there could be a potential privacy risk of machine learning sy…

AttributeBIG-bench Machine LearningPerceptual DistancePrivacy Preserving

Feature Losses for Adversarial Robustness

2019-12-10 · Kirthi Shankar Sivamani

Deep learning has made tremendous advances in computer vision tasks such as image classification. However, recent studies have shown that deep learning models are vulnerable to specifically crafted adversarial inputs tha…

Adversarial RobustnessDenoisingimage-classificationImage Classification