Forensicability of Deep Neural Network Inference Pipelines
Machine Learning
2021-02-19 v2 Cryptography and Security
Multimedia
Abstract
We propose methods to infer properties of the execution environment of machine learning pipelines by tracing characteristic numerical deviations in observable outputs. Results from a series of proof-of-concept experiments obtained on local and cloud-hosted machines give rise to possible forensic applications, such as the identification of the hardware platform used to produce deep neural network predictions. Finally, we introduce boundary samples that amplify the numerical deviations in order to distinguish machines by their predicted label only.
Cite
@article{arxiv.2102.00921,
title = {Forensicability of Deep Neural Network Inference Pipelines},
author = {Alexander Schlögl and Tobias Kupek and Rainer Böhme},
journal= {arXiv preprint arXiv:2102.00921},
year = {2021}
}
Comments
Accepted at ICASSP 2021