Detection of GAN-Generated Fake Images over Social Networks

By Francesco Marra, Diego Gragnaniello, Davide Cozzolino, Luisa Verdoliva. 2018

381 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

CNN-Generated Images Are Surprisingly Easy to Spot… for Now (2019, background): “[24] likewise showed that simple classifiers can detect images created by an image translation network [17], but did not consider cross-model transfer.”
The Creation and Detection of Deepfakes (2020, background): “In [106, 119, 131], it was shown that deep neural networks tend to perform beer than traditional image forensic tools on compressed imagery.”
ForensicTransfer: Weakly-supervised Domain Adaptation for Forgery Detection (2018, background): “Fewer works [30, 3] instead address the problem of detecting more recent form of manipulations, that use advanced computer graphics tools or artificial intelligence.”
Leveraging Frequency Analysis for Deep Fake Image Recognition (2020, methodology): “…has utilized these ﬁndings for identifying GAN-generated images: Marra et. al. provide a comparison of different steganalysis and CNN-based methods (Marra et al., 2018), several approaches use CNNs in the image domain (Mo et al., 2018; Yu et al., 2019a; Tariq et al., 2019), others use statistics…”
SpotFake: A Multi-modal Framework for Fake News Detection (2019, neutral): “[18] used GANs to detect fake images.”
Do GANs Leave Artificial Fingerprints? (2018, background): “Several architectures have been tested so far [17]–[19] showing a good accuracy in detecting GAN-generated images, even on compressed images.”
DIRE for Diffusion-Generated Image Detection (2023, background): “[26] study several classical deep CNN classifiers [18, 43, 7] to detect images generated by image-to-image translation networks.”
Watch Your Up-Convolution: CNN Based Generative Deep Neural Networks Are Failing to Reproduce Spectral Distributions (2020, background): “Most approaches reported in the literature, like [38, 3, 57], are themselves relying on CNNs and thus require large amounts of annotated training data.”
GANprintR: Improved Fakes and Evaluation of the State of the Art in Face Manipulation Detection (2019, background): “Finally, we also include for completeness some relevant references to other recent studies focused on the detection of general GAN-based image manipulations, not facial ones: [12], [35]–[38].”
Media Forensics and DeepFakes: An Overview (2020, methodology): “With reference to GAN images, a first investigation has been carried out in [171], where several CNN architectures have been tested in a supervised setting to discriminate GAN”
Source Generator Attribution via Inversion (2019, methodology): “A related problem is the detection of whether a given image was generated by any GAN-type generator, which has successfully been demonstrated by several groups using various meth-ods [18, 22, 7, 6, 14, 20].”
Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues (2020, methodology): “Recent methods [3, 33, 45, 46, 43, 58, 60, 30] use deep neural networks to extract high-level information from the spatial domain and get remarkable progress.”
Global Texture Enhancement for Fake Face Detection in the Wild (2020, background): “Recently, some researchers have investigated the problem of fake face detection [17, 26, 27, 23, 24, 32, 34, 30].”
Deepfakes generation and detection: state-of-the-art, open challenges, countermeasures, and way forward (2021, background): “Instead of focusing on a specific artifact, some approaches are data-driven, which detect manipulations by classification [157-177] or anomaly identification [178-182].”
Face X-Ray for More General Face Forgery Detection (2019, background): “This makes face forgery detection increasingly challenging, attracting a large number of research efforts [12, 44, 25, 32, 28, 18, 3, 22, 35, 36].”
Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints (2018, background): “GAN-generated images, several existing works [44, 47, 59] show good accuracy.”