arXiv (Cornell University) · 2019 · 57 citations · 14 references
ComputingComputer ScienceComputer VisionMachine LearningMachine VisionDeep LearningGenerative ModelingImage ClassificationImage CompressionPattern RecognitionRepresentation LearningAutoencodersClassification AccuracyClassification Accuracy AnalysisClassification Accuracy AssessmentDeep Learning-based ClassificationFrequency Spectrum AnalysisGenerative Adversarial NetworksTransformations
Advancements in deep generative models such as generative adversarial networks and variational autoencoders have resulted in the ability to generate realistic images that are visually indistinguishable from real images, which raises concerns about their potential malicious usage. In this paper, we present an analysis of the high-frequency Fourier modes of real and deep network generated images and show that deep network generated images share an observable, systematic shortcoming in replicating the attributes of these high-frequency modes. Using this, we propose a detection method based on the frequency spectrum of the images which is able to achieve an accuracy of up to 99.2% in classifying real and deep network generated images from various GAN and VAE architectures on a dataset of 5000 images with as few as 8 training examples. Furthermore, we show the impact of image transformations such as compression, cropping, and resolution reduction on the classification accuracy and suggest a method for modifying the high-frequency attributes of deep network generated images to mimic real images.
14
CNN-Generated Images Are Surprisingly Easy to Spot… for Now
Sheng-Yu Wang, Oliver Wang, Richard Zhang et al. · 2020 · 1K citations
Adversarially Learned Inference
Vincent Dumoulin, Ishmael Belghazi, Ben Poole et al. · arXiv (Cornell University) · 2016 · 692 citations · Full text