Defeating Image Obfuscation with Deep Learning

Abstract

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.

References in corpus (3)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Naive-Deep Face Recognition: Touching the Limit of LFW Benchmark or Not?
• Faceless Person Recognition; Privacy Implications in Social Media

Cited by in corpus (9)

• When Machine Learning Meets Privacy: A Survey and Outlook
• A Utility-Preserving GAN for Face Obscuration
• AnonymousNet: Natural Face De-Identification with Measurable Privacy
• Differentially Private Imaging via Latent Space Manipulation
• Obfuscation via Information Density Estimation
• DeepBlur: A Simple and Effective Method for Natural Image Obfuscation
• Temporally coherent video anonymization through GAN inpainting
• Linguistic Fingerprints of Internet Censorship: the Case of SinaWeibo
• Multitask Identity-Aware Image Steganography via Minimax Optimization