EyeSpy demonstrates a side-channel attack that reconstructs eye gaze from rendering performance variations in foveated rendering VR systems with mean errors of 1.1-4.4 degrees.
Sok: Data privacy in virtual reality
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.HC 2years
2026 2representative citing papers
A benchmark study evaluates standard and emerging deep learning architectures on motion data from 71 VR users, establishing performance baselines for user identification.
citing papers explorer
-
EyeSpy: Inferring Eye Gaze via Side-Channel Attacks Against Foveated Rendering
EyeSpy demonstrates a side-channel attack that reconstructs eye gaze from rendering performance variations in foveated rendering VR systems with mean errors of 1.1-4.4 degrees.
-
Deep Learning for Virtual Reality User Identification: A Benchmark
A benchmark study evaluates standard and emerging deep learning architectures on motion data from 71 VR users, establishing performance baselines for user identification.