Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Chi, Zhu, Tianqing, Shen, Sheng, Zhou, Wanlei
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2306.01364
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913186259664896
author Liu, Chi
Zhu, Tianqing
Shen, Sheng
Zhou, Wanlei
author_facet Liu, Chi
Zhu, Tianqing
Shen, Sheng
Zhou, Wanlei
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2306_01364
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Towards Robust GAN-generated Image Detection: a Multi-view Completion Representation
Liu, Chi
Zhu, Tianqing
Shen, Sheng
Zhou, Wanlei
Cryptography and Security
Computer Vision and Pattern Recognition
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.
title Towards Robust GAN-generated Image Detection: a Multi-view Completion Representation
topic Cryptography and Security
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2306.01364