Adversarial Attacks on Co-Occurrence Features for GAN Detection

Abstract

Improvements in Generative Adversarial Networks (GANs) have greatly reduced the difficulty of producing new, photo-realistic images with unique semantic meaning. With this rise in ability to generate fake images comes demand to detect them. While numerous methods have been developed for this task, the majority of them remain vulnerable to adversarial attacks. In this paper, develop two novel adversarial attacks on co-occurrence based GAN detectors. These are the first attacks to be presented against such a detector. We show that our method can reduce accuracy from over 98% to less than 4%, with no knowledge of the deep learning model or weights. Furthermore, accuracy can be reduced to 0% with full knowledge of the deep learning model details.

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• Towards Deep Learning Models Resistant to Adversarial Attacks
• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
• The Cityscapes Dataset for Semantic Urban Scene Understanding
• Semantic Image Synthesis with Spatially-Adaptive Normalization
• Spatially Transformed Adversarial Examples
• advertorch v0.1: An Adversarial Robustness Toolbox based on PyTorch
• Adversarial Manipulation of Deep Representations
• Detecting and Simulating Artifacts in GAN Fake Images
• GANprintR: Improved Fakes and Evaluation of the State of the Art in Face Manipulation Detection