Source Generator Attribution via Inversion

With advances in Generative Adversarial Networks (GANs) leading to dramatically-improved synthetic images and video, there is an increased need for algorithms which extend traditional forensics to this new category of imagery. While GANs have been shown to be helpful in a number of computer vision applications, there are other problematic uses such as `deep fakes' which necessitate such forensics. Source camera attribution algorithms using various cues have addressed this need for imagery captured by a camera, but there are fewer options for synthetic imagery. We address the problem of attributing a synthetic image to a specific generator in a white box setting, by inverting the process of generation. This enables us to simultaneously determine whether the generator produced the image and recover an input which produces a close match to the synthetic image.

[1]  Subarna Tripathi,et al.  Precise Recovery of Latent Vectors from Generative Adversarial Networks , 2017, ICLR.

[2]  Anil A. Bharath,et al.  Inverting the Generator of a Generative Adversarial Network , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[3]  Davide Cozzolino,et al.  Detection of GAN-Generated Fake Images over Social Networks , 2018, 2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR).

[4]  Thomas Hofmann,et al.  Generator Reversal , 2017, ArXiv.

[5]  Jiancheng Lv,et al.  Learning Inverse Mapping by AutoEncoder Based Generative Adversarial Nets , 2017, ICONIP.

[6]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[7]  Mario Fritz,et al.  Attributing Fake Images to GANs: Analyzing Fingerprints in Generated Images , 2018, ArXiv.

[8]  Luisa Verdoliva,et al.  Do GANs Leave Artificial Fingerprints? , 2018, 2019 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR).

[9]  Miroslav Goljan,et al.  Digital camera identification from sensor pattern noise , 2006, IEEE Transactions on Information Forensics and Security.

[10]  Yuichi Yoshida,et al.  Spectral Normalization for Generative Adversarial Networks , 2018, ICLR.

[11]  Nasir D. Memon,et al.  Blind source camera identification , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[12]  Edward J. Delp,et al.  Deepfake Video Detection Using Recurrent Neural Networks , 2018, 2018 15th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS).

[13]  Léon Bottou,et al.  Towards Principled Methods for Training Generative Adversarial Networks , 2017, ICLR.

[14]  Mo Chen,et al.  Source digital camcorder identification using sensor photo response non-uniformity , 2007, Electronic Imaging.

[15]  Edmund Y. Lam,et al.  Source camera identification using footprints from lens aberration , 2006, Electronic Imaging.

[16]  Julien Rabin,et al.  Detecting Overfitting of Deep Generative Networks via Latent Recovery , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Siwei Lyu,et al.  In Ictu Oculi: Exposing AI Created Fake Videos by Detecting Eye Blinking , 2018, 2018 IEEE International Workshop on Information Forensics and Security (WIFS).

[18]  Mario Fritz,et al.  Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints , 2018, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[19]  Chia-Yen Lee,et al.  Learning to Detect Fake Face Images in the Wild , 2018, 2018 International Symposium on Computer, Consumer and Control (IS3C).

[20]  B. S. Manjunath,et al.  Detecting GAN generated Fake Images using Co-occurrence Matrices , 2019, Media Watermarking, Security, and Forensics.

[21]  Alexei A. Efros,et al.  Generative Visual Manipulation on the Natural Image Manifold , 2016, ECCV.

[22]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[23]  Han Zhang,et al.  Self-Attention Generative Adversarial Networks , 2018, ICML.

[24]  Jaakko Lehtinen,et al.  Progressive Growing of GANs for Improved Quality, Stability, and Variation , 2017, ICLR.

[25]  Scott McCloskey,et al.  Detecting GAN-generated Imagery using Color Cues , 2018, ArXiv.