The paper entitled "Supervised Joint Nonlinear Transform Learning with Discriminative-Ambiguous Prior for Generic Privacy-Preserved Features" has been accepted for lecture presentation at 53rd Annual Conference on Information Systems & Sciences (CISS 2019), to be held Johns Hopkins University in Baltimore, Maryland. 



 

CISS2019_Behrooz1.png

 

Fig 1. Extracting the discriminative representation and ambiguous representation from the corresponding learned nonlinear transforms, and obtaining the final privacy-protected representation.

CISS2019_Behrooz2.png

 

Fig 2. Visualizing three classes of data (i) in the original domain and (ii) in the transform domain.