Detecting and tracing deepfakes using identity watermarks

Paper Title:

Robust Identity Perceptual Watermark Against Deepfake Face Swapping

Published on:

2 November 2023

Primary Category:

Computer Vision and Pattern Recognition

Paper Authors:

Tianyi Wang,

Mengxiao Huang,

Harry Cheng,

Bin Ma,

Yinglong Wang

Bullets

Key Details

•

Proposes identity perceptual watermarks with chaotic encryption for deepfake defense

•

Develops robust encoder-decoder framework to embed watermarks into facial images

•

Achieves concurrent deepfake detection and source image tracing

•

Demonstrates strong performance across datasets and face swapping algorithms

•

Outperforms existing watermarking and distortion methods for deepfake defense

Explore the topics in this paper

deepfakes

face swapping

image forensics

imperceptible watermarks

media authentication

AI generated summary

Detecting and tracing deepfakes using identity watermarks

This paper proposes a new method to detect deepfake face swapping manipulations and trace the original image source. It embeds imperceptible identity watermarks into facial images that contain semantic information about the face identity. A chaotic encryption system protects watermark confidentiality. The watermarks are encoded and recovered using an encoder-decoder neural network framework trained to be robust against common image manipulations and face swapping attacks. Experiments show this method has state-of-the-art performance in recovering watermarks and detecting fakes, even on unseen datasets and face swapping algorithms.