These tools and metrics are designed to help AI actors develop and use trustworthy AI systems and applications that respect human rights and are fair, transparent, explainable, robust, secure and safe.
Anonymity Set Size
The anonymity set for an individual u, denoted ASu is the set of users that the adversary cannot distinguish from u. It can be seen as the size of the crowd into which the target u can blend.
privASS ≡ |ASu |
Instead of users, anonymity sets can also be applied to locations, location pairs (e.g., home/work), or radio frequency identification (RFID) devices. As a result of its simplicity, the anonymity set size is widely used in the literature.
Related use cases :
Modelling Unlinkability
Uploaded on Nov 3, 2022While there have been made several proposals to define and measure anonymity (e.g., with information theory, formal languages and logics) unlinkability has not been modelled ge...
Adaptive Fusion of Single-View and Multi-View Depth for Autonomous Driving
Uploaded on Apr 2, 2024Self-supervised Video Object Segmentation with Distillation Learning of Deformable Attention
Uploaded on Apr 2, 2024You Only Need One Color Space: An Efficient Network for Low-light Image Enhancement
Uploaded on Apr 2, 2024About the metric
You can click on the links to see the associated metrics
Objective(s):
Purpose(s):
Target sector(s):
Lifecycle stage(s):
Target users:
Risk management stage(s):
