Robust Deepfake On Unrestricted Media: Generation And Detection
Not on the map. Why?
Abstract (arXiv)
Recent advances in deep learning have led to substantial improvements in deepfake generation, resulting in fake media with a more realistic appearance. Although deepfake media have potential application in a wide range of areas and are drawing much attention from both the academic and industrial communities, it also leads to serious social and criminal concerns. This chapter explores the evolution of and challenges in deepfake generation and detection. It also discusses possible ways to improve the robustness of deepfake detection for a wide variety of media (e.g., in-the-wild images and videos). Finally, it suggests a focus for future fake media research.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 89 of its 123 references that are in the map. First posted on arXiv 13 Feb 2022.
Builds on
89 of 123 references.
References · 89
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2017Mask R-CNNcited by 7,259
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
- 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
- 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
- 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
- 2016Adversarial examples in the physical worldcited by 1,762
- 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
- 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,176
- 2017A Closer Look at Spatiotemporal Convolutions for Action Recognitioncited by 1,139
38 more
- 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,095
- 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
- 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
- 2016Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networkscited by 895
- 2019Interpreting the Latent Space of GANs for Semantic Face Editingcited by 691
- 2020Face2Face: Real-time Face Capture and Reenactment of RGB Videoscited by 631
- 2019MaskGAN: Towards Diverse and Interactive Facial Image Manipulationcited by 624
- 2019Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensicscited by 573
- 2019Face X-ray for More General Face Forgery Detectioncited by 469
- 2019YOLACT: Real-time Instance Segmentationcited by 441
- 2018MesoNet: a Compact Facial Video Forgery Detection Networkcited by 409
- 2019FSGAN: Subject Agnostic Face Swapping and Reenactmentcited by 319
- 2018Exposing DeepFake Videos By Detecting Face Warping Artifactscited by 318
- 2020Conditional Convolutions for Instance Segmentationcited by 314
- 2018Exposing Deep Fakes Using Inconsistent Head Posescited by 294
- 2020Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detectioncited by 286
- 2019Few-Shot Adversarial Learning of Realistic Neural Talking Head Modelscited by 284
- 2018Deep Video Portraitscited by 265
- 2019Mask Scoring R-CNNcited by 265
- 2019On the Detection of Digital Face Manipulationcited by 259
- 2019Deferred Neural Rendering: Image Synthesis using Neural Texturescited by 253
- 2019SEAN: Image Synthesis with Semantic Region-Adaptive Normalizationcited by 253
- 2020DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detectioncited by 251
- 2021Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domaincited by 241
- 2019FaceShifter: Towards High Fidelity And Occlusion Aware Face Swappingcited by 221
- 2020Global Texture Enhancement for Fake Face Detection in the Wildcited by 220
- 2018DeepFakes: a New Threat to Face Recognition? Assessment and Detectioncited by 208
- 2021WildDeepfake: A Challenging Real-World Dataset for Deepfake Detectioncited by 207
- 2019CenterMask : Real-Time Anchor-Free Instance Segmentationcited by 200
- 2018X2Face: A network for controlling face generation by using images, audio, and pose codescited by 189
- 2019PolarMask: Single Shot Instance Segmentation with Polar Representationcited by 188
- 2018Capsule-Forensics: Using Capsule Networks to Detect Forged Images and Videoscited by 180
- 2020A Self-supervised Approach for Adversarial Robustnesscited by 180
- 2017Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognitioncited by 178
- 2020Adversarial Latent Autoencoderscited by 155
- 2020BlendMask: Top-Down Meets Bottom-Up for Instance Segmentationcited by 144
- 2021Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detectioncited by 133
- 2019Multi-task Learning For Detecting and Segmenting Manipulated Facial Images and Videoscited by 130
50 most cited of 89 All 89 (JSON)
Built on by
Citing papers per year: 2022: 2.
2 papers.