Profiling and Discriminating of Containerized ML Applications in Digital Data Marketplaces (DDM)

Lu Zhang, Reginald Cushing, Ralph Koning, Cees de Laat, Paola Grosso

2021

Abstract

A Digital Data Marketplace (DDM) facilitates secure and trustworthy data sharing among multiple parties. For instance, training a machine learning (ML) model using data from multiple parties normally contributes to higher prediction accuracy. It is crucial to enforce the data usage policies during the execution stage. In this paper, we propose a methodology to distinguish programs running inside containers by monitoring system calls sequence externally. To support container portability and the necessity of retraining ML models, we also investigate the stability of the proposed methodology in 7 typical containerized ML applications over different execution platform OSs and training data sets. The results show our proposed methodology can distinguish between applications over various configurations with an average classification accuracy of 93.85%, therefore it can be integrated as an enforcement component in DDM infrastructures.

Paper Citation

in Harvard Style

Zhang L., Cushing R., Koning R., de Laat C. and Grosso P. (2021). Profiling and Discriminating of Containerized ML Applications in Digital Data Marketplaces (DDM).In Proceedings of the 7th International Conference on Information Systems Security and Privacy - Volume 1: ICISSP, ISBN 978-989-758-491-6, pages 508-515. DOI: 10.5220/0010254105080515

in Bibtex Style

@conference{icissp21,
author={Lu Zhang and Reginald Cushing and Ralph Koning and Cees de Laat and Paola Grosso},
title={Profiling and Discriminating of Containerized ML Applications in Digital Data Marketplaces (DDM)},
booktitle={Proceedings of the 7th International Conference on Information Systems Security and Privacy - Volume 1: ICISSP,},
year={2021},
pages={508-515},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010254105080515},
isbn={978-989-758-491-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 7th International Conference on Information Systems Security and Privacy - Volume 1: ICISSP,
TI - Profiling and Discriminating of Containerized ML Applications in Digital Data Marketplaces (DDM)
SN - 978-989-758-491-6
AU - Zhang L.
AU - Cushing R.
AU - Koning R.
AU - de Laat C.
AU - Grosso P.
PY - 2021
SP - 508
EP - 515
DO - 10.5220/0010254105080515