Information-containing Adversarial Perturbation for Combating Facial Manipulation Systems
Preprint
Abstract
With the development of deep learning technology, the facial manipulation system has become powerful and easy to use. Such systems can modify the attributes of the given facial images, such as hair color, gender, and age. Malicious applications of such systems pose a serious threat to individuals' privacy and reputation. Existing studies have proposed various approaches to protect images against facial manipulations. Passive defense methods aim to detect whether the face is real or fake, which works for posterior forensics but can not prevent malicious manipulation. Initiative defense methods protect images upfront by injecting adversarial perturbations into images to disrupt facial manipulation systems but can not identify whether the image is fake. To address the limitation of existing methods, we propose a novel two-tier protection method named Information-containing Adversarial Perturbation (IAP), which provides more comprehensive protection for {facial images}. We use an encoder to map a facial image and its identity message to a cross-model adversarial example which can disrupt multiple facial manipulation systems to achieve initiative protection. Recovering the message in adversarial examples with a decoder serves passive protection, contributing to provenance tracking and fake image detection. We introduce a feature-level correlation measurement that is more suitable to measure the difference between the facial images than the commonly used mean squared error. Moreover, we propose a spectral diffusion method to spread messages to different frequency channels, thereby improving the robustness of the message against facial manipulation. Extensive experimental results demonstrate that our proposed IAP can recover the messages from the adversarial examples with high average accuracy and effectively disrupt the facial manipulation systems.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- MTD-Net: Learning to Detect Deepfakes Images by Multi-Scale Texture DifferenceIEEE Transactions on Information Forensics and Security, 2021
- Who Is in Control? Practical Physical Layer Attack and Defense for mmWave-Based Sensing in Autonomous VehiclesIEEE Transactions on Information Forensics and Security, 2021
- Decomposed Meta Batch Normalization for Fast Domain Adaptation in Face RecognitionIEEE Transactions on Information Forensics and Security, 2021
- PFA-GAN: Progressive Face Aging With Generative Adversarial NetworkIEEE Transactions on Information Forensics and Security, 2020
- Preventing DeepFake Attacks on Speaker Authentication by Dynamic Lip Movement AnalysisIEEE Transactions on Information Forensics and Security, 2020
- Towards Transferable Adversarial Attack Against Deep Face RecognitionIEEE Transactions on Information Forensics and Security, 2020
- Unsupervised Adversarial Domain Adaptation for Cross-Domain Face Presentation Attack DetectionIEEE Transactions on Information Forensics and Security, 2020
- Regulating deep fakes: legal and ethical considerationsJournal of Intellectual Property Law & Practice, 2020
- Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks2017
- Digital watermarking: algorithms and applicationsIEEE Signal Processing Magazine, 2001