Defeating Image Obfuscation with Deep Learning
read the original 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.
This paper has not been read by Pith yet.
Forward citations
Cited by 4 Pith papers
-
PPEDCRF: Dynamic-CRF-Guided Selective Perturbation for Background-Based Location Privacy in Video Sequences
Selective DCRF-guided perturbation of background regions reduces video location retrieval accuracy while preserving ~6 dB higher PSNR than global Gaussian noise.
-
Privacy-Preserving Structureless Visual Localization via Image Obfuscation
Simple image obfuscation enables privacy-preserving structureless visual localization with standard feature matchers and no pipeline changes, achieving state-of-the-art accuracy among privacy methods.
-
A Common Pool of Privacy Problems: Legal and Technical Lessons from a Large-Scale Web-Scraped Machine Learning Dataset
An empirical audit of one web-scraped ML training dataset reveals persistent PII after sanitization, which the authors combine with legal analysis to highlight privacy risks and advocate redefining 'publicly available...
-
A Utility-Preserving GAN for Face Obscuration
UP-GAN uses a GAN to obscure faces while preserving utility attributes like age, gender, pose, and expression better than blurring or pixelation.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.