TAFIM: Targeted Adversarial Attacks against Facial Image Manipulations
Authors:
Preprint
Abstract
Face manipulation methods can be misused to affect an individual's privacy or to spread disinformation. To this end, we introduce a novel data-driven approach that produces image-specific perturbations which are embedded in the original images. The key idea is that these protected images prevent face manipulation by causing the manipulation model to produce a predefined manipulation target (uniformly colored output image in our case) instead of the actual manipulation. In addition, we propose to leverage differentiable compression approximation, hence making generated perturbations robust to common image compression. In order to prevent against multiple manipulation methods simultaneously, we further propose a novel attention-based fusion of manipulation-specific perturbations. Compared to traditional adversarial attacks that optimize noise patterns for each image individually, our generalized model only needs a single forward pass, thus running orders of magnitude faster and allowing for easy integration in image processing stacks, even on resource-constrained devices like smartphones.Keywords
All Related Versions
This publication has 20 references indexed in Scilit:
- Disrupting Deepfakes: Adversarial Attacks Against Conditional Image Translation Networks and Facial Manipulation Systems2020
- A Style-Based Generator Architecture for Generative Adversarial Networks2019
- Exposing Deep Fakes Using Inconsistent Head Poses2019
- Capsule-forensics: Using Capsule Networks to Detect Forged Images and Videos2019
- HiDDeN: Hiding Data With Deep Networks2018
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric2018
- Two-Stream Neural Networks for Tampered Face Detection2017
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Exposing Region Splicing Forgeries with Blind Local Noise EstimationInternational Journal of Computer Vision, 2013
- The JPEG still picture compression standardIEEE Transactions on Consumer Electronics, 1992