Security News > 2022 > January > Researchers use GPU fingerprinting to track users online
A team of researchers from French, Israeli, and Australian universities has explored the possibility of using people's GPUs to create unique fingerprints and use them for persistent web tracking.
The researchers considered the possibility of creating distinctive fingerprints based on the GPU of the tracked systems with the help of WebGL. WebGL is a cross-platform API for rendering 3D graphics in the browser, and it's present on all modern web browsers.
DrawnApart uses short GLSL programs executed by the target GPU as part of the vertex shader to overcome the challenge of having random execution units handling the computations.
Apart from these conditions, workload variations, GPU payloads from other web browser tabs, system restarts, and other runtime changes don't affect DrawnApart.
The next-gen GPU APIs currently in development, most notably WebGPU, features compute shaders which come in addition to the existing graphics pipeline.
When the researchers tested compute shaders in the now-abandoned WebGL 2.0, they found that DrawnApart delivered 98% classification accuracy in just 150 milliseconds, much faster than the 8 seconds used to collect fingerprinting data through the WebGL API. "We believe that a similar method can also be found for the WebGPU API once it becomes generally available. The effects of accelerated compute APIs on user privacy should be considered before they are enabled globally," concludes the research paper.