Proceedings chapter
Open access

Privacy-Preserving Image Sharing Via Sparsifying Layers on Convolutional Groups

Presented at Barcelona (Spain), 4-8 May 2020
Publication date2020

We propose a practical framework to address the problem of privacy-aware image sharing in large-scale setups. We argue that, while compactness is always desired at scale, this need is more severe when trying to furthermore protect the privacy-sensitive content. We therefore encode images, such that, from one hand, representations are stored in the public domain without paying the huge cost of privacy protection, but ambiguated and hence leaking no discernible content from the images, unless a combinatorially-expensive guessing mechanism is available for the attacker. From the other hand, authorized users are provided with very compact keys that can easily be kept secure. This can be used to disambiguate and reconstruct faithfully the corresponding access-granted images. We achieve this with a convolutional autoencoder of our design, where feature maps are passed independently through sparsifying transformations, providing multiple compact codes, each responsible for reconstructing different attributes of the image. The framework is tested on a large-scale database of images with public implementation available.

  • Privacy-preserving image sharing
  • Convolutional autoencoders
  • Sparse representation
  • Learned compression
  • Image obfuscation
Citation (ISO format)
FERDOWSI, Sohrab et al. Privacy-Preserving Image Sharing Via Sparsifying Layers on Convolutional Groups. In: 2020 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2020. Barcelona (Spain). [s.l.] : IEEE, 2020. p. 2797–2801. doi: 10.1109/ICASSP40776.2020.9054046
Main files (1)
Proceedings chapter (Published version)

Technical informations

Creation10/20/2020 2:03:00 PM
First validation10/20/2020 2:03:00 PM
Update time03/15/2023 11:35:10 PM
Status update03/15/2023 11:35:09 PM
Last indexation02/01/2024 10:56:21 AM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack