loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Joshua Stock 1 ; Lucas Lange 2 ; Erhard Rahm 2 and Hannes Federrath 1

Affiliations: 1 Security in Distributed Systems, Universität Hamburg, Germany ; 2 Database Group, Universität Leizpig, Germany

Keyword(s): Machine Learning, Privacy Attacks, Property Inference, Defense Mechanisms, Adversarial Training.

Abstract: In contrast to privacy attacks focussing on individuals in a training dataset (e.g., membership inference), Property Inference Attacks (PIAs) are aimed at extracting population-level properties from trained Machine Learning (ML) models. These sensitive properties are often based on ratios, such as the ratio of male to female records in a dataset. If a company has trained an ML model on customer data, a PIA could for example reveal the demographics of their customer base to a competitor, compromising a potential trade secret. For ratio-based properties, inferring over a continuous range using regression is more natural than classification. We therefore extend previous white-box and black-box attacks by modelling property inference as a regression problem. For the black-box attack we further reduce prior assumptions by using an arbitrary attack dataset, independent from a target model’s training data. We conduct experiments on three datasets for both white-box and black-box scenarios, indicating promising adversary performances in each scenario with a test R² between 0.6 and 0.86. We then present a new defense mechanism based on adversarial training that successfully inhibits our black-box attacks. This mechanism proves to be effective in reducing the adversary’s R² from 0.63 to 0.07 and induces practically no utility loss, with the accuracy of target models dropping by no more than 0.2 percentage points. (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 3.138.126.124

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:
Stock, J.; Lange, L.; Rahm, E. and Federrath, H. (2024). Property Inference as a Regression Problem: Attacks and Defense. In Proceedings of the 21st International Conference on Security and Cryptography - SECRYPT; ISBN 978-989-758-709-2; ISSN 2184-7711, SciTePress, pages 876-885. DOI: 10.5220/0012863800003767

@conference{secrypt24,
author={Joshua Stock. and Lucas Lange. and Erhard Rahm. and Hannes Federrath.},
title={Property Inference as a Regression Problem: Attacks and Defense},
booktitle={Proceedings of the 21st International Conference on Security and Cryptography - SECRYPT},
year={2024},
pages={876-885},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012863800003767},
isbn={978-989-758-709-2},
issn={2184-7711},
}

TY - CONF

JO - Proceedings of the 21st International Conference on Security and Cryptography - SECRYPT
TI - Property Inference as a Regression Problem: Attacks and Defense
SN - 978-989-758-709-2
IS - 2184-7711
AU - Stock, J.
AU - Lange, L.
AU - Rahm, E.
AU - Federrath, H.
PY - 2024
SP - 876
EP - 885
DO - 10.5220/0012863800003767
PB - SciTePress