Towards Robust GAN-generated Image Detection: a Multi-view Completion Representation

06/02/2023
by   Chi Liu, et al.
0

GAN-generated image detection now becomes the first line of defense against the malicious uses of machine-synthesized image manipulations such as deepfakes. Although some existing detectors work well in detecting clean, known GAN samples, their success is largely attributable to overfitting unstable features such as frequency artifacts, which will cause failures when facing unknown GANs or perturbation attacks. To overcome the issue, we propose a robust detection framework based on a novel multi-view image completion representation. The framework first learns various view-to-image tasks to model the diverse distributions of genuine images. Frequency-irrelevant features can be represented from the distributional discrepancies characterized by the completion models, which are stable, generalized, and robust for detecting unknown fake patterns. Then, a multi-view classification is devised with elaborated intra- and inter-view learning strategies to enhance view-specific feature representation and cross-view feature aggregation, respectively. We evaluated the generalization ability of our framework across six popular GANs at different resolutions and its robustness against a broad range of perturbation attacks. The results confirm our method's improved effectiveness, generalization, and robustness over various baselines.

READ FULL TEXT

page 3

page 7

research
02/07/2022

FrePGAN: Robust Deepfake Detection Using Frequency-level Perturbations

Various deepfake detectors have been proposed, but challenges still exis...
research
03/26/2022

Fusing Global and Local Features for Generalized AI-Synthesized Image Detection

With the development of the Generative Adversarial Networks (GANs) and D...
research
06/19/2020

Adversarial Attacks for Multi-view Deep Models

Recent work has highlighted the vulnerability of many deep machine learn...
research
04/19/2018

Multi-view Hybrid Embedding: A Divide-and-Conquer Approach

We present a novel cross-view classification algorithm where the gallery...
research
12/27/2022

General GAN-generated image detection by data augmentation in fingerprint domain

In this work, we investigate improving the generalizability of GAN-gener...
research
08/22/2023

IT3D: Improved Text-to-3D Generation with Explicit View Synthesis

Recent strides in Text-to-3D techniques have been propelled by distillin...
research
05/09/2019

Limits of Deepfake Detection: A Robust Estimation Viewpoint

Deepfake detection is formulated as a hypothesis testing problem to clas...

Please sign up or login with your details

Forgot password? Click here to reset