Paper 2021/131

Privacy-Preserving Video Classification with Convolutional Neural Networks

Sikha Pentyala, Rafael Dowsley, and Martine De Cock


Many video classification applications require access to personal data, thereby posing an invasive security risk to the users' privacy. We propose a privacy-preserving implementation of single-frame method based video classification with convolutional neural networks that allows a party to infer a label from a video without necessitating the video owner to disclose their video to other entities in an unencrypted manner. Similarly, our approach removes the requirement of the classifier owner from revealing their model parameters to outside entities in plaintext. To this end, we combine existing Secure Multi-Party Computation (MPC) protocols for private image classification with our novel MPC protocols for oblivious single-frame selection and secure label aggregation across frames. The result is an end-to-end privacy-preserving video classification pipeline. We evaluate our proposed solution in an application for private human emotion recognition. Our results across a variety of security settings, spanning honest and dishonest majority configurations of the computing parties, and for both passive and active adversaries, demonstrate that videos can be classified with state-of-the-art accuracy, and without leaking sensitive user information.

Available format(s)
Cryptographic protocols
Publication info
Preprint. MINOR revision.
Contact author(s)
sikha @ uw edu
rafael dowsley @ monash edu
mdecock @ uw edu
2021-02-06: received
Short URL
Creative Commons Attribution


      author = {Sikha Pentyala and Rafael Dowsley and Martine De Cock},
      title = {Privacy-Preserving Video Classification with Convolutional Neural Networks},
      howpublished = {Cryptology ePrint Archive, Paper 2021/131},
      year = {2021},
      note = {\url{}},
      url = {}
Note: In order to protect the privacy of readers, does not use cookies or embedded third party content.