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.
This metric counts the information items S disclosed by a system, e.g., the number of compromised users. However, this metric does not indicate the severity of a leak because it does not account for the
sensitivity of the leaked information.
privALI ≡ |S |
Related use cases :
Privacy-preserving genomic computation through program specialization
Uploaded on Nov 3, 2022In this paper, we present a new approach to performing important classes of genomic computations (e.g., search for homologous genes) that makes a significant step towards priva...
About 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: