New Study Reveals Motion Data can identify People in VR

The study, led by graduate researcher Vivek Nair at the University of California Berkeley and conducted at the Center for Responsible Decentralized Intelligence (RDI), looked at data collected from over ten thousand users of the VR application Beat Saber. Over the past few years, Beat Saber has become a widely popular VR rhythm game.

Modern virtual reality headsets with multiple cameras, Microphones and sensors collect various data: user facial features, voice timbre, eye movements, as well as objects around the home or office. In the future, it may also be possible to install EEG sensors that read brain activity signals through the scalp. And even if you take out all this phrasing, it’s still not possible to verify anonymity – enough to identify a person, analyzing simple data about his movements.

The metaverse is a term coined to describe a virtual reality space where users can interact with each other in a variety of ways. To enter and engage in the Metaverse, users wear 3D headsets that cover their eyes, allowing them to see what is happening around them in the virtual world. Other hardware includes hand sensors allowing users to interact with other people and virtual objects.

As the Metaverse has grown more sophisticated in recent years, the experience has become more immersive – sometimes people forget they’re actually there. This has led many in the community to wonder about their privacy when interacting in the metaverse. Early attempts to learn more about privacy in the Metaverse have shown little to no privacy—virtually all activity is traceable to the user. In this new effort, the team in California explored a new way to discover the identities of users visiting a given virtual world: studying body movements.

The researchers also explored general applications of the findings for VR gaming, including advanced cheating detection, score prediction, skill-based matchmaking, and map recommendation engines. Going forward, researchers believe it is essential to develop defensive technologies that can protect user privacy while preserving the usefulness of VR applications.

Protecting user privacy in the Metaverse is very difficult. As an alternative, the researchers proposed transmitting data from the sensors to intermediate sources that detect errors. But this means loss of enjoyment of reported noise, reduced accuracy in VR headsets and games that require physical skill. There is also an alternative option – the introduction of industry regulations prohibiting Metaverse platforms from storing and analyzing human movement data. Such regulations are intended to protect the public, but such requirements are not easy to enforce – industry certainly resists.