loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Lucas Lange 1 ; Maja Schneider 1 ; Peter Christen 2 and Erhard Rahm 1

Affiliations: 1 Leipzig University & ScaDS.AI Dresden/Leipzig, Leipzig, Germany ; 2 The Australian National University, Canberra, Australia

Keyword(s): Privacy-Preserving Machine Learning, Differential Privacy, Membership Inference Attack, Practical Privacy, COVID-19 Detection, Differentially-Private Stochastic Gradient Descent.

Abstract: Machine learning (ML) can help fight pandemics like COVID-19 by enabling rapid screening of large volumes of images. To perform data analysis while maintaining patient privacy, we create ML models that satisfy Differential Privacy (DP). Previous works exploring private COVID-19 models are in part based on small datasets, provide weaker or unclear privacy guarantees, and do not investigate practical privacy. We suggest improvements to address these open gaps. We account for inherent class imbalances and evaluate the utility-privacy trade-off more extensively and over stricter privacy budgets. Our evaluation is supported by empirically estimating practical privacy through black-box Membership Inference Attacks (MIAs). The introduced DP should help limit leakage threats posed by MIAs, and our practical analysis is the first to test this hypothesis on the COVID-19 classification task. Our results indicate that needed privacy levels might differ based on the task-dependent practical threa t from MIAs. The results further suggest that with increasing DP guarantees, empirical privacy leakage only improves marginally, and DP therefore appears to have a limited impact on practical MIA defense. Our findings identify possibilities for better utility-privacy trade-offs, and we believe that empirical attack-specific privacy estimation can play a vital role in tuning for practical privacy. (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 3.238.82.77

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:
Lange, L.; Schneider, M.; Christen, P. and Rahm, E. (2023). Privacy in Practice: Private COVID-19 Detection in X-Ray Images. In Proceedings of the 20th International Conference on Security and Cryptography - SECRYPT; ISBN 978-989-758-666-8; ISSN 2184-7711, SciTePress, pages 624-633. DOI: 10.5220/0012048100003555

@conference{secrypt23,
author={Lucas Lange. and Maja Schneider. and Peter Christen. and Erhard Rahm.},
title={Privacy in Practice: Private COVID-19 Detection in X-Ray Images},
booktitle={Proceedings of the 20th International Conference on Security and Cryptography - SECRYPT},
year={2023},
pages={624-633},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012048100003555},
isbn={978-989-758-666-8},
issn={2184-7711},
}

TY - CONF

JO - Proceedings of the 20th International Conference on Security and Cryptography - SECRYPT
TI - Privacy in Practice: Private COVID-19 Detection in X-Ray Images
SN - 978-989-758-666-8
IS - 2184-7711
AU - Lange, L.
AU - Schneider, M.
AU - Christen, P.
AU - Rahm, E.
PY - 2023
SP - 624
EP - 633
DO - 10.5220/0012048100003555
PB - SciTePress