Fighting Deepfake by Exposing the Convolutional Traces on Images
Citations
3,940 citations
134 citations
Cites methods from "Fighting Deepfake by Exposing the C..."
...Using convolutional traces on GAN-based images [162] KNN, SVM, and LDA Training the expectation-maximization algorithm [163] to detect and extract discriminative features via a fingerprint that represents the convolutional traces left by GANs during image generation....
[...]
35 citations
24 citations
21 citations
References
38,211 citations
"Fighting Deepfake by Exposing the C..." refers background in this paper
...Advances in Artificial Intelligence, and specifically, the advent of Generative Adversarial Networks (GAN) [3], enabled the creation and widespread of extremely refined techniques able to attack digital data, alter it or create its contents from scratch....
[...]
30,124 citations
"Fighting Deepfake by Exposing the C..." refers background in this paper
...Figure 5 shows a visual representation by means of t-SNE [30]: it is possible to notice how Deepfakes can be ‘‘linearly’’ separable from authentic samples....
[...]
11,682 citations
6,884 citations
6,759 citations
"Fighting Deepfake by Exposing the C..." refers background in this paper
...Once trained, the fundamental element involved in the image creation is the generator G which is composed of Transpose Convolution layers [28]....
[...]