Modeling Deep Learning Based Privacy Attacks on Physical Mail

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.

arXiv commentSource code: https://github.com/BingyaoHuang/Neural-STE

References in corpus (12)

• Adam: A Method for Stochastic Optimization
• Measuring the Transmission Matrix in Optics : An Approach to the Study and Control of Light Propagation in Disordered Media
• Non-invasive real-time imaging through scattering layers and around corners via speckle correlations
• Image Transmission Through an Opaque Material
• High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
• Reference-less measurement of the transmission matrix of a highly scattering material using a DMD and phase retrieval techniques
• Translation correlations in anisotropically scattering media
• Efficient and accurate inversion of multiple scattering with deep learning
• Learning-based real-time method to looking through scattering medium beyond the memory effect
• Physics-Based Generative Adversarial Models for Image Restoration and Beyond
• Imaging through glass diffusers using densely connected convolutional networks
• Neural Blind Deconvolution Using Deep Priors