DiffProtect: Generate Adversarial Examples with Diffusion Models for Facial Privacy Protection

05/23/2023
by   Jiang Liu, et al.
0

The increasingly pervasive facial recognition (FR) systems raise serious concerns about personal privacy, especially for billions of users who have publicly shared their photos on social media. Several attempts have been made to protect individuals from being identified by unauthorized FR systems utilizing adversarial attacks to generate encrypted face images. However, existing methods suffer from poor visual quality or low attack success rates, which limit their utility. Recently, diffusion models have achieved tremendous success in image generation. In this work, we ask: can diffusion models be used to generate adversarial examples to improve both visual quality and attack performance? We propose DiffProtect, which utilizes a diffusion autoencoder to generate semantically meaningful perturbations on FR systems. Extensive experiments demonstrate that DiffProtect produces more natural-looking encrypted images than state-of-the-art methods while achieving significantly higher attack success rates, e.g., 24.5 CelebA-HQ and FFHQ datasets.

READ FULL TEXT

page 1

page 4

page 6

page 7

page 8

page 13

page 14

research
05/22/2023

Attribute-Guided Encryption with Facial Texture Masking

The increasingly pervasive facial recognition (FR) systems raise serious...
research
03/07/2022

Protecting Facial Privacy: Generating Adversarial Identity Masks via Style-robust Makeup Transfer

While deep face recognition (FR) systems have shown amazing performance ...
research
05/14/2023

Diffusion Models for Imperceptible and Transferable Adversarial Attack

Many existing adversarial attacks generate L_p-norm perturbations on ima...
research
10/20/2020

Preventing Personal Data Theft in Images with Adversarial ML

Facial recognition tools are becoming exceptionally accurate in identify...
research
02/15/2023

Data Forensics in Diffusion Models: A Systematic Analysis of Membership Privacy

In recent years, diffusion models have achieved tremendous success in th...
research
06/26/2023

3D-Aware Adversarial Makeup Generation for Facial Privacy Protection

The privacy and security of face data on social media are facing unprece...
research
05/06/2023

Towards Prompt-robust Face Privacy Protection via Adversarial Decoupling Augmentation Framework

Denoising diffusion models have shown remarkable potential in various ge...

Please sign up or login with your details

Forgot password? Click here to reset