Please use this identifier to cite or link to this item: https://doi.org/10.1109/SP.2019.00065
Title: Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning
Authors: Milad Nasr
REZA SHOKRI 
Amir Houmansadr
Issue Date: 19-May-2019
Publisher: IEEE
Citation: Milad Nasr, REZA SHOKRI, Amir Houmansadr (2019-05-19). Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning. IEEE Symposium on Security and Privacy (SP). ScholarBank@NUS Repository. https://doi.org/10.1109/SP.2019.00065
Abstract: Deep neural networks are susceptible to various inference attacks as they remember information about their training data. We design white-box inference attacks to perform a comprehensive privacy analysis of deep learning models. We measure the privacy leakage through parameters of fully trained models as well as the parameter updates of models during training. We design inference algorithms for both centralized and federated learning, with respect to passive and active inference attackers, and assuming different adversary prior knowledge. We evaluate our novel white-box membership inference attacks against deep learning algorithms to trace their training data records. We show that a straightforward extension of the known black-box attacks to the white-box setting (through analyzing the outputs of activation functions) is ineffective. We therefore design new algorithms tailored to the white-box setting by exploiting the privacy vulnerabilities of the stochastic gradient descent algorithm, which is the algorithm used to train deep neural networks. We investigate the reasons why deep learning models may leak information about their training data. We then show that even well-generalized models are significantly susceptible to white-box membership inference attacks, by analyzing state-of-the-art pre-trained and publicly available models for the CIFAR dataset. We also show how adversarial participants, in the federated learning setting, can successfully run active membership inference attacks against other participants, even when the global model achieves high prediction accuracies.
Source Title: IEEE Symposium on Security and Privacy (SP)
URI: https://scholarbank.nus.edu.sg/handle/10635/168423
ISBN: 978-1-5386-6660-9
DOI: 10.1109/SP.2019.00065
Appears in Collections:Staff Publications
Elements

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
Shokri-SP2019.pdf435.41 kBAdobe PDF

OPEN

NoneView/Download

SCOPUSTM   
Citations

7
checked on Jun 4, 2020

Page view(s)

25
checked on Jun 4, 2020

Download(s)

5
checked on Jun 4, 2020

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.