Journal article
Making Generated Images Hard To Spot: A Transferable Attack On Synthetic Image Detectors
25 Apr 2021
Abstract
International Conference on Pattern Recognition, August 2022,
Montr\'eal Qu\'ebec Visually realistic GAN-generated images have recently emerged as an important
misinformation threat. Research has shown that these synthetic images contain
forensic traces that are readily identifiable by forensic detectors.
Unfortunately, these detectors are built upon neural networks, which are
vulnerable to recently developed adversarial attacks. In this paper, we propose
a new anti-forensic attack capable of fooling GAN-generated image detectors.
Our attack uses an adversarially trained generator to synthesize traces that
these detectors associate with real images. Furthermore, we propose a technique
to train our attack so that it can achieve transferability, i.e. it can fool
unknown CNNs that it was not explicitly trained against. We evaluate our attack
through an extensive set of experiments, where we show that our attack can fool
eight state-of-the-art detection CNNs with synthetic images created using seven
different GANs, and outperform other alternative attacks.
Metrics
2 Record Views
Details
- Title
- Making Generated Images Hard To Spot: A Transferable Attack On Synthetic Image Detectors
- Creators
- Xinwei ZhaoMatthew C Stamm
- Resource Type
- Journal article
- Language
- English
- Academic Unit
- Electrical and Computer Engineering
- Identifiers
- 991019295315204721