2019

FakeSpotter: A Simple yet Robust Baseline for Spotting AI-Synthesized Fake Faces

Wang, Run, Juefei-Xu, Felix, Ma, Lei et al.

Understand

In recent years, generative adversarial networks (GANs) and its variants have achieved unprecedented success in image synthesis.

They are widely adopted in synthesizing facial images which brings potential security concerns to humans as the fakes spread and fuel the misinformation.
However, robust detectors of these AI-synthesized fake faces are still in their infancy and are not ready to fully tackle this emerging challenge.
In this work, we propose a novel approach, named FakeSpotter, based on monitoring neuron behaviors to spot AI-synthesized fake faces.

Built on

Counter-forensics: Attacking image forensics
Rainer Böhme and Matthias Kirchner · 2013
Earlier work this paper cites.
Generative adversarial nets
Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio · 2014
Earlier work this paper cites.
Explaining and harnessing adversarial examples
Ian Goodfellow, Jonathon Shlens, and Christian Szegedy · 2015
Earlier work this paper cites.
Deep learning face attributes in the wild
Ziwei Liu, Ping Luo, Xiaogang W., and X. Tang · 2015
Earlier work this paper cites.
Understanding deep image representations by inverting them
Aravindh Mahendran and Andrea Vedaldi · 2015
Earlier work this paper cites.
Simultaneous Forgery Identification and Localization in Paintings Using Advanced Correlation Filters
P. Buchana, I. Cazan, M. Diaz-Granados, F. Juefei-Xu, and M.Savvides · 2016
Earlier work this paper cites.
DeepXplore: Automated whitebox testing of deep learning systems
Kexin Pei, Yinzhi Cao, Junfeng Yang, and Suman Jana · 2017
Earlier work this paper cites.
Dualgan: Unsupervised dual learning for image-to-image translation
Zili Yi, Hao Zhang, Ping Tan, and Minglun Gong · 2017
Earlier work this paper cites.
Unpaired image-to-image translation using cycle-consistent adversarial networks
Jun-Yan Zhu, Taesung Park, Phillip Isola, and Alexei A Efros · 2017
Earlier work this paper cites.
StarGAN: Unified generative adversarial networks for multi-domain image-to-image translation
Yunjey Choi, Minje Choi, Munyoung Kim, Jung-Woo Ha, Sunghun Kim, and Jaegul Choo · 2018
Earlier work this paper cites.
We Are Truly F—ed: Everyone Is Making AI-Generated Fake Porn Now
Samantha Cole · 2018
Earlier work this paper cites.
Progressive growing of GANs for improved quality, stability, and variation
Tero Karras, Timo Aila, Samuli Laine, and Jaakko Lehtinen · 2018
Earlier work this paper cites.
Deepfakes: a new threat to face recognition? assessment and detection
Original
Pavel Korshunov and Sébastien Marcel · 2018
Earlier work this paper cites.

Similar

DeepGauge: Multi-granularity testing criteria for deep learning systems
Lei Ma, Felix Juefei-Xu, Fuyuan Zhang, Jiyuan Sun, Minhui Xue, Bo Li, Chunyang Chen, Ting Su, Li Li, Yang Liu, et al · 2018
Cited alongside, same era.
Deepmutation: Mutation testing of deep learning systems
Lei Ma, Fuyuan Zhang, Jiyuan Sun, Minhui Xue, Bo Li, Felix Juefei-Xu, Chao Xie, Li Li, Yang Liu, Jianjun Zhao, et al · 2018
Cited alongside, same era.
Detecting GAN-generated imagery using color cues
Original
Scott McCloskey and Michael Albright · 2018
Cited alongside, same era.
Protecting world leaders against deep fakes
Shruti Agarwal, Hany Farid, Yuming Gu, Mingming He, Koki Nagano, and Hao Li · 2019
Cited alongside, same era.
A style-based generator architecture for generative adversarial networks
Tero Karras, Samuli Laine, and Timo Aila · 2019
Cited alongside, same era.
Analyzing and improving the image quality of stylegan
Original
Tero Karras, Samuli Laine, Miika Aittala, Janne Hellsten, Jaakko Lehtinen, and Timo Aila · 2019
Cited alongside, same era.
Exposing deepfake videos by detecting face warping artifacts
Yuezun Li and Siwei Lyu · 2019
Cited alongside, same era.
Celeb-DF: A new dataset for deepfake forensics
Original
Yuezun Li, Xin Yang, Pu Sun, Honggang Qi, and Siwei Lyu · 2019
Cited alongside, same era.
STGAN: A unified selective transfer network for arbitrary image attribute editing
Ming Liu, Yukang Ding, Min Xia, Xiao Liu, Errui Ding, Wangmeng Zuo, and Shilei Wen · 2019
Cited alongside, same era.
Deepct: Tomographic combinatorial testing for deep learning systems
Lei Ma, Felix Juefei-Xu, Minhui Xue, Bo Li, Li Li, Yang Liu, and Jianjun Zhao · 2019
Cited alongside, same era.
NIC: Detecting adversarial samples with neural network invariant checking
Shiqing Ma, Yingqi Liu, Guanhong Tao, Wen-Chuan Lee, and Xiangyu Zhang · 2019
Cited alongside, same era.
Detecting GAN generated fake images using co-occurrence matrices
Original
Lakshmanan Nataraj, Tajuddin Manhar Mohammed, BS Manjunath, Shivkumar Chandrasekaran, Arjuna Flenner, Jawadul H Bappy, and Amit K Roy-Chowdhury · 2019
Cited alongside, same era.

Then

FaceForensics++: Learning to detect manipulated facial images
Andreas Rössler, Davide Cozzolino, Luisa Verdoliva, Christian Riess, Justus Thies, and Matthias Nießner · 2019
Closest in time.
Amora: Black-box Adversarial Morphing Attack
Original
Run Wang, Felix Juefei-Xu, Xiaofei Xie, Lei Ma, Yihao Huang, and Yang Liu · 2019
Closest in time.
DeepHunter: a coverage-guided fuzz testing framework for deep neural networks
Xiaofei Xie, Lei Ma, Felix Juefei-Xu, Minhui Xue, Hongxu Chen, Yang Liu, Jianjun Zhao, Bo Li, Jianxiong Yin, and Simon See · 2019
Closest in time.
Exposing deep fakes using inconsistent head poses
Xin Yang, Yuezun Li, and Siwei Lyu · 2019
Closest in time.
Attributing fake images to gans: Learning and analyzing gan fingerprints
Ning Yu, Larry S Davis, and Mario Fritz · 2019
Closest in time.
Few-shot adversarial learning of realistic neural talking head models
Original
Egor Zakharov, Aliaksandra Shysheya, Egor Burkov, and Victor Lempitsky · 2019
Closest in time.
Machine learning testing: Survey, landscapes and horizons
Original
Jie M Zhang, Mark Harman, Lei Ma, and Yang Liu · 2019
Closest in time.
Detecting and simulating artifacts in gan fake images
Original
Xu Zhang, Svebor Karaman, and Shih-Fu Chang · 2019
Closest in time.
ABBA: Saliency-Regularized Motion-Based Adversarial Blur Attack
Original
Qing Guo, Felix Juefei-Xu, Xiaofei Xie, Lei Ma, Jian Wang, Wei Feng, and Yang Liu · 2020
Closest in time.
FakeLocator: Robust Localization of GAN-Based Face Manipulations
Original
Yihao Huang, Felix Juefei-Xu, Run Wang, Qing Guo, Xiaofei Xie, Lei Ma, Jianwen Li, Weikai Miao, Yang Liu, and Geguang Pu · 2020
Closest in time.
On the detection of digital face manipulation
Joel Stehouwer, Hao Dang, Feng Liu, Xiaoming Liu, and Anil Jain · 2020
Closest in time.
CNN-generated images are surprisingly easy to spot… for now
Sheng-Yu Wang, Oliver Wang, Richard Zhang, Andrew Owens, and Alexei A Efros · 2020
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…