Thursday, 20th of May 2021, 12:00 – 1:00

Forensicability of Deep Neural Network Inference Pipelines

Please use this link & sign in with your real name

Alex Schlögl
Researcher at SEC, University of Innsbruck


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.




Nach oben scrollen