Electromagnetic emanations from a VR headset can be classified with a nearby software-defined radio and a fine-tuned ResNet to identify the running VR app and the user's activity, with a claimed accuracy near 99%.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NI 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
VReaves: Eavesdropping on Virtual Reality App Identity and Activity via Electromagnetic Side Channels
Electromagnetic emanations from a VR headset can be classified with a nearby software-defined radio and a fine-tuned ResNet to identify the running VR app and the user's activity, with a claimed accuracy near 99%.