1 Hit in 2.3 sec

Learning Representations for Anonymizing Sensor Data in IoT Applications

Omid Hajihassani
As the first contribution of this thesis, we investigate the ability of variational autoencoder (VAE) models to learn representations that enable hiding the private information embedded in sensor data.  ...  These manipulations effectively support data anonymization when the corresponding latent variable is used to reconstruct ii  ...  ObscureNet conditions the decoder on the private attributes (similar to a CVAE) and performs adversarial information factorization to ensure that learned latent representations are invariant to private  ... 
doi:10.7939/r3-fr93-x367 fatcat:ikgmlp5mirdp5ee3jkqqemykme