Modeling Deep Learning Based Privacy Attacks on Physical Mail

Authors

  • Bingyao Huang Stony Brook University
  • Ruyi Lian Stony Brook University
  • Dimitris Samaras Stony Brook University
  • Haibin Ling Stony Brook University

Keywords:

Ethics -- Bias, Fairness, Transparency & Privacy

Abstract

Mail privacy protection aims to prevent unauthorized access to hidden content within an envelope since normal paper envelopes are not as safe as we think. In this paper, for the first time, we show that with a well designed deep learning model, the hidden content may be largely recovered without opening the envelope. We start by modeling deep learning-based privacy attacks on physical mail content as learning the mapping from the camera-captured envelope front face image to the hidden content, then we explicitly model the mapping as a combination of perspective transformation, image dehazing and denoising using a deep convolutional neural network, named Neural-STE (See-Through-Envelope). We show experimentally that hidden content details, such as texture and image structure, can be clearly recovered. Finally, our formulation and model allow us to design envelopes that can counter deep learning-based privacy attacks on physical mail.

Downloads

Published

2021-05-18

How to Cite

Huang, B., Lian, R., Samaras, D., & Ling, H. (2021). Modeling Deep Learning Based Privacy Attacks on Physical Mail. Proceedings of the AAAI Conference on Artificial Intelligence, 35(2), 1593-1601. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16251

Issue

Section

AAAI Technical Track on Computer Vision I