DeepAI AI Chat
Log In Sign Up

FakePolisher: Making DeepFakes More Detection-Evasive by Shallow Reconstruction

by   Yihao Huang, et al.

The recently rapid advances of generative adversarial networks (GANs) in synthesizing realistic and natural DeepFake information (e.g., images, video) cause severe concerns and threats to our society. At this moment, GAN-based image generation methods are still imperfect, whose upsampling design has limitations in leaving some certain artifact patterns in the synthesized image. Such artifact patterns can be easily exploited (by recent methods) for difference detection of real and GAN-synthesized images. To reduce the artifacts in the synthesized images, deep reconstruction techniques are usually futile because the process itself can leave traces of artifacts. In this paper, we devise a simple yet powerful approach termed FakePolisher that performs shallow reconstruction of fake images through learned linear dictionary, intending to effectively and efficiently reduce the artifacts introduced during image synthesis. The comprehensive evaluation on 3 state-of-the-art DeepFake detection methods and fake images generated by 16 popular GAN-based fake image generation techniques, demonstrates the effectiveness of our technique.


page 1

page 5

page 6


CycleGAN without checkerboard artifacts for counter-forensics of fake-image detection

In this paper, we propose a novel CycleGAN without checkerboard artifact...

Misleading Deep-Fake Detection with GAN Fingerprints

Generative adversarial networks (GANs) have made remarkable progress in ...

FakeRetouch: Evading DeepFakes Detection via the Guidance of Deliberate Noise

The novelty and creativity of DeepFake generation techniques have attrac...

What makes fake images detectable? Understanding properties that generalize

The quality of image generation and manipulation is reaching impressive ...

DeepSonar: Towards Effective and Robust Detection of AI-Synthesized Fake Voices

With the recent advances in voice synthesis, AI-synthesized fake voices ...

Parents and Children: Distinguishing Multimodal DeepFakes from Natural Images

Recent advancements in diffusion models have enabled the generation of r...

Fighting Deepfake by Exposing the Convolutional Traces on Images

Advances in Artificial Intelligence and Image Processing are changing th...

Code Repositories