Paper ID | IFS-1.5 | ||
Paper Title | FORENSICABILITY OF DEEP NEURAL NETWORK INFERENCE PIPELINES | ||
Authors | Alexander Schlögl, Tobias Kupek, Rainer Böhme, University of Innsbruck, Austria | ||
Session | IFS-1: Multimedia Forensics 1 | ||
Location | Gather.Town | ||
Session Time: | Tuesday, 08 June, 13:00 - 13:45 | ||
Presentation Time: | Tuesday, 08 June, 13:00 - 13:45 | ||
Presentation | Poster | ||
Topic | Information Forensics and Security: [MMF] Multimedia Forensics | ||
IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
Abstract | We propose methods to infer properties of the execution envi-ronment of machine learning pipelines by tracing characteris-tic numerical deviations in observable outputs. Results from aseries of proof-of-concept experiments obtained on local andcloud-hosted machines give raise to possible forensic applica-tions, such as the identification of the hardware platform usedto produce deep neural network predictions. Finally, we intro-duce boundary samples that amplify the numerical deviationsin order to distinguish machines by their predicted label only. |