A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf
.
Privacy Vulnerability of Split Computing to Data-Free Model Inversion Attacks
[article]
2022
arXiv
pre-print
Mobile edge devices see increased demands in deep neural networks (DNNs) inference while suffering from stringent constraints in computing resources. Split computing (SC) emerges as a popular approach to the issue by executing only initial layers on devices and offloading the remaining to the cloud. Prior works usually assume that SC offers privacy benefits as only intermediate features, instead of private data, are shared from devices to the cloud. In this work, we debunk this SC-induced
arXiv:2107.06304v2
fatcat:v3bk55cmz5antimbu2nvhz3lfi