Pattern Detection in the Activation Space for Identifying Synthesized Content

by   Celia Cintas, et al.

Generative Adversarial Networks (GANs) have recently achieved unprecedented success in photo-realistic image synthesis from low-dimensional random noise. The ability to synthesize high-quality content at a large scale brings potential risks as the generated samples may lead to misinformation that can create severe social, political, health, and business hazards. We propose SubsetGAN to identify generated content by detecting a subset of anomalous node-activations in the inner layers of pre-trained neural networks. These nodes, as a group, maximize a non-parametric measure of divergence away from the expected distribution of activations created from real data. This enable us to identify synthesised images without prior knowledge of their distribution. SubsetGAN efficiently scores subsets of nodes and returns the group of nodes within the pre-trained classifier that contributed to the maximum score. The classifier can be a general fake classifier trained over samples from multiple sources or the discriminator network from different GANs. Our approach shows consistently higher detection power than existing detection methods across several state-of-the-art GANs (PGGAN, StarGAN, and CycleGAN) and over different proportions of generated content.



There are no comments yet.


page 2


Subset Scanning Over Neural Network Activations

This work views neural networks as data generating systems and applies a...

Fighting deepfakes by detecting GAN DCT anomalies

Synthetic multimedia content created through AI technologies, such as Ge...

FDFtNet: Facing Off Fake Images using Fake Detection Fine-tuning Network

Creating fake images and videos such as "Deepfake" has become much easie...

Learning to Detect Fake Face Images in the Wild

Although Generative Adversarial Network (GAN) can be used to generate th...

On the Role of Receptive Field in Unsupervised Sim-to-Real Image Translation

Generative Adversarial Networks (GANs) are now widely used for photo-rea...

Synthesize-It-Classifier: Learning a Generative Classifier through RecurrentSelf-analysis

In this work, we show the generative capability of an image classifier n...

PRE-render Content Using Tiles (PRECUT). 1. Large-Scale Compound-Target Relationship Analyses

Visualizing a complex network is computationally intensive process and d...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.