AVP-Inspect: Coordinated Cyber-Physical Testing for Privacy Analysis of COTS Apple Vision Pro Applications
AVP-Inspect automated testing finds 58% of 324 Apple Vision Pro apps show privacy violations, with over 60% of network traffic flows undisclosed.
Researchers built AVP-Inspect, a dynamic analysis framework combining custom hardware device control, 3D UI exploration, and a unified privacy taxonomy for Apple Vision Pro. Testing 324 App Store apps for 20 minutes each found 188 (58.0%) with at least one privacy violation. More than 60% of observed network traffic flows were not properly disclosed, extending prior XR privacy work beyond Android-based devices such as Meta Quest.
- First large-scale automated privacy analysis of Apple Vision Pro applications via network traffic
- Coordinates cyber and physical control to overcome the closed AVP ecosystem
- Finds 188 of 324 apps (58.0%) exhibit at least one privacy violation
- Over 60% of network traffic flows lack proper disclosure
- Constructs a unified privacy taxonomy for AVP applications
From the original article
1 min read at arxiv.orgXR devices introduce substantial privacy concerns due to their comprehensive data collection capabilities that surpass traditional computing platforms.
By Yichang Xiong · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.