Sebastian Raschka 8/2/2018

Generating Gender-Neutral Face Images with Semi-Adversarial Neural Networks to Enhance Privacy

Read Original

This article details a research project on using semi-adversarial neural networks to perturb gender information in face images. The goal is to maximize privacy by preventing reliable gender classification while preserving the image's utility for biometric face recognition, helping to prevent profiling and identity theft. It references two academic papers and discusses applications like GDPR compliance.

Generating Gender-Neutral Face Images with Semi-Adversarial Neural Networks to Enhance Privacy

Comments

No comments yet

Be the first to share your thoughts!

Browser Extension

Get instant access to AllDevBlogs from your browser

Top of the Week