MGGA: Universal Perturbations against Deepfake via Multiple Model-based Gradient-Guided Feature Layer Attack
Open Access
- 27 October 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 73-82
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (62371350,62171326,62202340)
- Fundamental Research Funds for the Central Universities (2042025kf0054)
- Natural Science Foundation of Hubei Province (2025AFB455)
- Key Science and Technology Research Project of Xinjiang Production and Construction Corps in 2025
- Kunshan Municipal Government Research Funding, Seed Fund for Sino Foreign Joint Research Platform between Wuhan University and Duke Kunshan University
- Alar City Science and Technology Plan Project (2024ZB02)
This publication has 41 references indexed in Scilit:
- Watch Your Steps: Local Image and Scene Editing by Text Instructions2024
- Depth map guided triplet network for deepfake face detectionNeural Networks, 2022
- Two-Branch Recurrent Network for Isolating Deepfakes in Videos2020
- Disrupting Deepfakes: Adversarial Attacks Against Conditional Image Translation Networks and Facial Manipulation Systems2020
- Deepfake Video Detection Using Recurrent Neural Networks2018
- Transferable Adversarial Perturbations2018
- GANimation: Anatomically-Aware Facial Animation from a Single Image2018
- Distortion-Aware Convolutional Filters for Dense Prediction in Panoramic Images2018
- Boosting Adversarial Attacks with Momentum2018
- StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation2018