2016/09/01 by Richard McPherson, Reza Shokri, McPherson, Richard +3 · 2 voices · 7 citations
Computer Science · #Digital Media Forensic Detection #Generative Adversarial Networks and Image Synthesis #Advanced Steganography and Watermarking Techniques
paper · pdf · doi:10.48550/arxiv.1609.00408
We demonstrate that modern image recognition methods based on artificial neural networks can recover hidden information from images protected by various forms of obfuscation. The obfuscation techniques considered in this paper are mosaicing (also known as pixelation), blurring (as used by YouTube), and P3, a recently proposed system for privacy-preserving photo sharing that encrypts the significant JPEG coefficients to make images unrecognizable by humans. We empirically show how to train artificial neural networks to successfully identify faces and recognize objects and handwritten digits even if the images are protected using any of the above obfuscation techniques.