loading
Papers Papers/2020

Research.Publish.Connect.

Paper

Authors: Daniel Felps 1 ; Amelia Schwickerath 1 ; Joyce Williams 1 ; Trung Vuong 1 ; Alan Briggs 2 ; Matthew Hunt 2 ; Evan Sakmar 2 ; David Saranchak 2 and Tyler Shumaker 2

Affiliations: 1 National Geospatial-Intelligence Agency, 7500 GEOINT Drive, Springfield, VA, U.S.A. ; 2 Concurrent Technologies Corporation, 100 CTC Drive, Johnstown, PA, U.S.A.

Keyword(s): Machine Unlearning, Data Redaction, Membership Inference Attack, Data Poisoning Attack.

Abstract: Individuals are gaining more control of their personal data through recent data privacy laws such the General Data Protection Regulation and the California Consumer Privacy Act. One aspect of these laws is the ability to request a business to delete private information, the so called “right to be forgotten” or “right to erasure”. These laws have serious financial implications for companies and organizations that train large, highly accurate deep neural networks (DNNs) using these valuable consumer data sets. However, a received redaction request poses complex technical challenges on how to comply with the law while fulfilling core business operations. We introduce a DNN model lifecycle maintenance process that establishes how to handle specific data redaction requests and minimize the need to completely retrain the model. Our process is based upon the membership inference attack as a compliance tool for every point in the training set. These attack models quantify the privacy risk of all training data points and form the basis of follow-on data redaction from an accurate deployed model; excision is implemented through incorrect label assignment within incremental model updates. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 54.80.173.217

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Felps, D.; Schwickerath, A.; Williams, J.; Vuong, T.; Briggs, A.; Hunt, M.; Sakmar, E.; Saranchak, D. and Shumaker, T. (2021). Class Clown: Data Redaction in Machine Unlearning at Enterprise Scale. In Proceedings of the 10th International Conference on Operations Research and Enterprise Systems - ICORES, ISBN 978-989-758-485-5; ISSN 2184-4372, pages 7-14. DOI: 10.5220/0010419600070014

@conference{icores21,
author={Daniel Felps. and Amelia Schwickerath. and Joyce Williams. and Trung Vuong. and Alan Briggs. and Matthew Hunt. and Evan Sakmar. and David Saranchak. and Tyler Shumaker.},
title={Class Clown: Data Redaction in Machine Unlearning at Enterprise Scale},
booktitle={Proceedings of the 10th International Conference on Operations Research and Enterprise Systems - ICORES,},
year={2021},
pages={7-14},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010419600070014},
isbn={978-989-758-485-5},
issn={2184-4372},
}

TY - CONF

JO - Proceedings of the 10th International Conference on Operations Research and Enterprise Systems - ICORES,
TI - Class Clown: Data Redaction in Machine Unlearning at Enterprise Scale
SN - 978-989-758-485-5
IS - 2184-4372
AU - Felps, D.
AU - Schwickerath, A.
AU - Williams, J.
AU - Vuong, T.
AU - Briggs, A.
AU - Hunt, M.
AU - Sakmar, E.
AU - Saranchak, D.
AU - Shumaker, T.
PY - 2021
SP - 7
EP - 14
DO - 10.5220/0010419600070014

0123movie.net