DiffProtect: Generate Adversarial Examples with Diffusion Models for Facial Privacy Protection
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911295456935936 |
|---|---|
| author | Liu, Jiang Lau, Chun Pong Guo, Zhongliang Guo, Yuxiang Wang, Zhaoyang Chellappa, Rama |
| author_facet | Liu, Jiang Lau, Chun Pong Guo, Zhongliang Guo, Yuxiang Wang, Zhaoyang Chellappa, Rama |
| contents | 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% and 25.1% absolute improvements on the CelebA-HQ and FFHQ datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_13625 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | DiffProtect: Generate Adversarial Examples with Diffusion Models for Facial Privacy Protection Liu, Jiang Lau, Chun Pong Guo, Zhongliang Guo, Yuxiang Wang, Zhaoyang Chellappa, Rama Computer Vision and Pattern Recognition Cryptography and Security 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% and 25.1% absolute improvements on the CelebA-HQ and FFHQ datasets. |
| title | DiffProtect: Generate Adversarial Examples with Diffusion Models for Facial Privacy Protection |
| topic | Computer Vision and Pattern Recognition Cryptography and Security |
| url | https://arxiv.org/abs/2305.13625 |