Please use this identifier to cite or link to this item: https://doi.org/10.1145/3461702.3462533
Title: On the Privacy Risks of Model Explanations
Authors: Shokri, R 
Strobel, M
Zick, Y 
Keywords: cs.LG
cs.LG
stat.ML
Issue Date: 21-Jul-2021
Publisher: ACM
Citation: Shokri, R, Strobel, M, Zick, Y (2021-07-21). On the Privacy Risks of Model Explanations. AIES 2021 - Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society abs/1907.00164 : 231-241. ScholarBank@NUS Repository. https://doi.org/10.1145/3461702.3462533
Abstract: Privacy and transparency are two key foundations of trustworthy machine learning. Model explanations offer insights into a model's decisions on input data, whereas privacy is primarily concerned with protecting information about the training data. We analyze connections between model explanations and the leakage of sensitive information about the model's training set. We investigate the privacy risks of feature-based model explanations using membership inference attacks: quantifying how much model predictions plus their explanations leak information about the presence of a datapoint in the training set of a model. We extensively evaluate membership inference attacks based on feature-based model explanations, over a variety of datasets. We show that backpropagation-based explanations can leak a significant amount of information about individual training datapoints. This is because they reveal statistical information about the decision boundaries of the model about an input, which can reveal its membership. We also empirically investigate the trade-off between privacy and explanation quality, by studying the perturbation-based model explanations.
Source Title: AIES 2021 - Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society
URI: https://scholarbank.nus.edu.sg/handle/10635/211756
DOI: 10.1145/3461702.3462533
Appears in Collections:Elements
Staff Publications

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
1907.00164v6.pdf814.49 kBAdobe PDF

OPEN

Post-printView/Download

SCOPUSTM   
Citations

12
checked on Jan 26, 2023

Page view(s)

86
checked on Jan 26, 2023

Download(s)

1
checked on Jan 26, 2023

Google ScholarTM

Check

Altmetric


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