Deepfakes Generation and Detection: A Short Survey
Abstract
:1. Introduction
2. Deepfake Generation and Detection
2.1. Identity Swap
2.1.1. Identity Swap Generation
2.1.2. Identity Swap Detection
2.2. Face Reenactment
2.2.1. Face Reenactment Generation
2.2.2. Face Reenactment Detection
2.3. Attribute Manipulation
2.3.1. Attribute Manipulation Generation
3.5. Mobile Deepfake Detector
3.6. Lack of Large-Scale ML-Generated Databases
3.7. Reproducible Research
4. Conclusions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Available online: https://theconversation.com/3-2-billion-images-and-720-000-hours-of-video-are-shared-online-daily-can-you-sort-real-from-fake-148630 (accessed on 4 January 2023).
- Available online: https://www.nbcnews.com/business/consumer/so-it-s-fine-if-you-edit-your-selfies-not-n766186 (accessed on 4 January 2023).
- Dolhansky, B.; Bitton, J.; Pflaum, B.; Lu, J.; Howes, R.; Wang, M.; Ferrer, C. The deepfake detection challenge dataset. ar**, and Face Perception. In Proceedings of the 13th IEEE International Conference on Automatic Face & Gesture Recognition, **,+and+Face+Perception&conference=Proceedings+of+the+13th+IEEE+International+Conference+on+Automatic+Face+&+Gesture+Recognition&author=Nirkin,+Y.&author=Masi,+I.&author=Tuan,+A.T.&author=Hassner,+T.&author=Medioni,+G.&publication_year=2018&pages=98%E2%80%93105" class='google-scholar' target='_blank' rel='noopener noreferrer'>Google Scholar]
- Mahajan, S.; Chen, L.; Tsai, T. SwapItUp: A Face Swap Application for Privacy Protection. In Proceedings of the IEEE 31st International Conference on Advanced Information Networking and Applications (AINA), Taipei, Taiwan, 27–29 March 2017; pp. 46–50. [Google Scholar]
- Wang, H.; Dongliang, X.; Wei, L. Robust and Real-Time Face Swap** Based on Face Segmentation and CANDIDE-3. In Proceedings of the PRICAI 2018: Trends in Artificial Intelligence, Nan**g, China, 28–31 August 2018; pp. 335–342. [Google Scholar]
- Natsume, R.; Yatagawa, T.; Morishima, S. RSGAN: Face Swap** and Editing Using Face and Hair Representation in Latent Spaces. ar**+and+Editing+Using+Face+and+Hair+Representation+in+Latent+Spaces&author=Natsume,+R.&author=Yatagawa,+T.&author=Morishima,+S.&publication_year=2018&journal=ar**. ar**&author=Li,+L.&author=Bao,+J.&author=Yang,+H.&author=Chen,+D.&author=Wen,+F.&publication_year=2019&journal=ar** for Forgery Detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 19–13 June 2020; pp. 5073–5082. [Google Scholar]
- Chen, R.; Chen, X.; Ni, B.; Ge, Y. SimSwap: An Efficient Framework For High Fidelity Face Swap**. In Proceedings of the 28th ACM International Conference on Multimedia, Seattle, WA, USA, 12–16 October 2020; pp. 2003–2011. [Google Scholar]
- Koopman, M.; Rodriguez, A.; Geradts, Z. Detection of deepfake video manipulation. In Proceedings of the 20th Irish Machine Vision and Image Processing Conference (IMVIP), Coleraine, UK, 29–31 August 2018; pp. 133–136. [Google Scholar]
- Li, Y.; Lyu, S. Exposing DeepFake Videos by Detecting Face War** Artifacts. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Long Beach, CA, USA, 16–17 June 2019; pp. 1–7. [Google Scholar]
- Li, Y.; Chang, M.; Lyu, S. In ictu oculi: Exposing ai generated fake face videos by detecting eye blinking. ar** and reenactment. In Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Korea, 27 October–2 November 2019; pp. 7184–7193. [Google Scholar]
- Zhang, J.; Zeng, X.; Wang, M.; Pan, Y.; Liu, L.; Liu, Y.; Ding, Y.; Fan, C. Freenet: Multi-identity face reenactment. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, 13–19 June 2020; pp. 5326–5335. [Google Scholar]
- Doukas, M.; Koujan, M.; Sharmanska, V.; Roussos, A.; Zafeiriou, S. Head2Head++: Deep Facial Attributes Re-Targeting. IEEE Trans. Biom. Behav. Identity Sci. 2021, 3, 31–43. [Google Scholar] [CrossRef]
- Cao, M.; Huang, H.; Wang, H.; Wang, X.; Shen, L.; Wang, S.; Bao, L.; Li, L.; Luo, J. Task-agnostic Temporally Consistent Facial Video Editing. ar**. ar**&author=Xu,+Z.&author=Hong,+Z.&author=Ding,+C.&author=Zhu,+Z.&author=Han,+J.&author=Liu,+J.&author=Ding,+E.&publication_year=2022&journal=ar** in the Wild. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA, 18–24 June 2022; pp. 10789–10798. [Google Scholar]
- Chung, J.S.; Nagrani, A.; Zisserman, A. Voxceleb2: Deepspeaker recognition. In Proceedings of the IEEE Conf. Conference of the International Speech Communication Association, Hyderabad, India, 2–6 September 2018; pp. 1–6. [Google Scholar]
- Afchar, D.; Nozick, V.; Yamagishi, J.; Echizen, I. Mesonet: A compact facial video forgery detection network. In Proceedings of the IEEE International Workshop on Information Forensics and Security (WIFS), Montpellier, France, 7–10 December 2021; pp. 1–7. [Google Scholar]
- Miao, C.; Chu, Q.; Li, W.; Gong, T.; Zhuang, W.; Yu, N. Towards Generalizable and Robust Face Manipulation Detection via Bag-of-local-feature. ar** and Reenactment. In Proceedings of the Asian Conference on Computer Vision, Kyoto, Japan, 30 November–4 December 2020; pp. 1–17. [Google Scholar]
- Shen, J.; Zafeiriou, S.; Chrysos, G.G.; Kossaifi, J.; Tzimiropoulos, G.; Pantic, M. The first facial landmark tracking in-the-wild challenge: Benchmark and results. In Proceedings of the IEEE International Conference on Computer Vision Workshops, Santiago, Chile, 7–13 December 2015; pp. 50–58. [Google Scholar]
- Tripathy, S.; Kannala, J.; Rahtu, E. FACEGAN: Facial Attribute Controllable rEenactment GAN. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, Virtual, 5–9 January 2021; pp. 1329–1338. [Google Scholar]
- Bounareli, S.; Argyriou, V.; Tzimiropoulos, G. Finding Directions in GAN’s Latent Space for Neural Face Reenactment. ar**v 2022, ar**v:2202.00046. [Google Scholar]
- Nagrani, A.; Chung, J.S.; Zisserman, A. Voxceleb: A large-scale speaker identification dataset. In Proceedings of the INTERSPEECH, Stockholm, Sweden, 20–24 August 2017; pp. 1–6. [Google Scholar]
- Agarwal, M.; Mukhopadhyay, R.; Namboodiri, V.; Jawahar, C. Audio-visual face reenactment. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, Waikoloa, HI, USA, 3–7 January 2023; pp. 5178–5187. [Google Scholar]
- Nguyen, H.; Fang, F.; Yamagishi, J.; Echizen, I. Multi-task Learning For Detecting and Segmenting Manipulated Facial Images and Videos. ar**v 2019, ar**v:1906.06876. [Google Scholar]
- Dang, H.; Liu, F.; Stehouwer, J.; Liu, X.; Jain, A. On the Detection of Digital Face Manipulation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, 13–19 June 2020; pp. 1–10. [Google Scholar]
- Kim, M.; Tariq, S.; Woo, S. FReTAL: Generalizing Deepfake Detection using Knowledge Distillation and Representation Learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA, 20–25 June 2021; pp. 1001–1012. [Google Scholar]
- Yu, P.; Fei, J.; **a, Z.; Zhou, Z.; Weng, J. Improving Generalization by Commonality Learning in Face Forgery Detection. IEEE Trans. Inf. Secur. 2022, 17, 547–558. [Google Scholar] [CrossRef]
- Wu, H.; Wang, P.; Wang, X.; **ang, J.; Gong, R. GGViT:Multistream Vision Transformer Network in Face2Face Facial Reenactment Detection. In Proceedings of the 2022 26th International Conference on Pattern Recognition (ICPR), Montreal, QC, Canada, 21–25 August 2022; pp. 2335–2341. [Google Scholar]
- Lample, G.; Zeghidour, N.; Usunier, N.; Bordes, A.; Denoyer, L.; Ranzato, M. Fader networks: Manipulating images by sliding attributes. ar**v 2017, ar**v:1706.00409. [Google Scholar]
- Liu, M.; Ding, Y.; **a, M.; Liu, X.; Ding, E.; Zuo, W.; Wen, S. STGAN: A unified selective transfer network for arbitrary image attribute editing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, 15–20 June 2019; pp. 3673–3682. [Google Scholar]
- Kim, H.; Choi, Y.; Kim, J.; Yoo, S.; Uh, Y. Exploiting Spatial Dimensions of Latent in GAN for Real-Time Image Editing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA, 20–25 June 2021; pp. 852–861. [Google Scholar]
- Choi, Y.; Uh, Y.; Yoo, J.; Ha, J. StarGAN v2: Diverse image synthesis for multiple domains. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, 13–19 June 2020; pp. 8188–8197. [Google Scholar]
- Huang, W.; Tu, S.; Xu, L. IA-FaceS: A Bidirectional Method for Semantic Face Editing. Neural Netw. 2023, 158, 272–292. [Google Scholar] [CrossRef] [PubMed]
- Sun, J.; Wang, X.; Zhang, Y.; Li, X.; Zhang, Q.; Liu, Y.; Wang, J. Fenerf: Face editing in neural radiance fields. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA, 18–24 June 2022; pp. 7672–7682. [Google Scholar]
- Wang, S.; Wang, O.; Owens, A.; Zhang, R.; Efros, A. Detecting photoshopped faces by scripting photoshop. In Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea, 27 October–2 November 2019; pp. 10072–10081. [Google Scholar]
- Du CX, T.; Trung, H.T.; Tam, P.M.; Hung NQ, V.; Jo, J. Efficient-Frequency: A hybrid visual forensic framework for facial forgery detection. In Proceedings of the IEEE Symposium Series on Computational Intelligence (SSCI), Canberra, Australia, 1–4 December 2020; pp. 707–712. [Google Scholar]
- Deepfake in the Wild Dataset. Available online: https://github.com/deepfakeinthewild/deepfake-in-the-wild (accessed on 4 January 2023).
- Rathgeb, C.; Nichols, R.; Ibsen, M.; Drozdowski, P.; Busch, C. Busch. Crowd-powered Face Manipulation Detection: Fusing Human Examiner Decisions. ar**v 2022, ar**v:2201.13084. [Google Scholar]
- Phillips, P.; Wechsler, H.; Huang, J.; Rauss, P.J. The FERET database and evaluation procedure for face-recognition algorithms. Image Vis. Comput. 1998, 16, 295–306. [Google Scholar] [CrossRef]
- Guo, Z.; Yang, G.; Zhang, D.; **a, M. Rethinking gradient operator for exposing AI-enabled face forgeries. Expert Syst. Appl. 2023, 215. [Google Scholar] [CrossRef]
- Li, Y.; Chen, X.; Wu, F.; Zha, Z.J. Linestofacephoto: Face photo generation from lines with conditional self-attention generative adversarial networks. In Proceedings of the 27th ACM International Conference on Multimedia, Nice, France, 21–25 October 2019; pp. 2323–2331. [Google Scholar]
- **a, W.; Yang, Y.; Xue, J.H.; Wu, B. TediGAN: Text-Guided Diverse Face Image Generation and Manipulation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA, 20–25 June 2021; pp. 2256–2265. [Google Scholar]
- Song, H.; Woo, S.; Lee, J.; Yang, S.; Cho, H.; Lee, Y.; Choi, D.; Kim, K. Talking Face Generation with Multilingual TTS. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA, 18–24 June 2022; pp. 21425–21430. [Google Scholar]
- Zen, H.; Dang, V.; Clark, R.; Zhang, Y.; Weiss, R.J.; Jia, Y.; Chen, Z.; Wu, Y. LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech. Interspeech 2019. [Google Scholar] [CrossRef] [Green Version]
- Shi, Y.; Bu, H.; Xu, X.; Zhang, S.; Li, M. AISHELL-3: A Multi-Speaker Mandarin TTS Corpus. Interspeech 2021. [Google Scholar] [CrossRef]
- Li, Z.; Min, M.; Li, K.; Xu, C. StyleT2I: Toward Compositional and High-Fidelity Text-to-Image Synthesis. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA, 18–24 June 2022; pp. 18197–18207. [Google Scholar]
- Wang, S.; Wang, O.; Zhang, R.; Owens, A.; Efros, A. CNN-generated images are surprisingly easy to spot… for now. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, 13–19 June 2020; pp. 8695–8704. [Google Scholar]
- Pu, J.; Mangaokar, N.; Wang, B.; Reddy, C.; Viswanath, B. Noisescope: Detecting deepfake images in a blind setting. In Proceedings of the Annual Computer Security Applications Conference, Austin, TX, USA, 6–10 December 2020; pp. 913–927. [Google Scholar]
- Yousaf, B.; Usama, M.; Sultani, W.; Mahmood, A.; Qadir, J. Fake visual content detection using two-stream convolutional neural networks. Neural Comput. Appl. 2022, 34, 7991–8004. [Google Scholar] [CrossRef]
- Nowroozi, E.; Conti, M.; Mekdad, Y. Detecting high-quality GAN-generated face images using neural networks. ar**v 2022, ar**v:2203.01716. [Google Scholar]
- Ferreira, A.; Nowroozi, E.; Barni, M. VIPPrint: Validating Synthetic Image Detection and Source Linking Methods on a Large Scale Dataset of Printed Documents. J. Imaging 2021, 7, 50. [Google Scholar] [CrossRef]
- Boyd, A.; Tinsley, P.; Bowyer, K.; Czajka, A. CYBORG: Blending Human Saliency Into the Loss Improves Deep Learning-Based Synthetic Face Detection. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, Waikoloa, Hawaii, 3–7 January 2023; pp. 6108–6117. [Google Scholar]
- Karras, T.; Aittala, M.; Hellsten, J.; Laine, S.; Lehtinen, J.; Aila, T. Training generative adversarial networks with limited data. Adv. Neural Inf. Process. Syst. 2020, 33, 12104–12114. [Google Scholar]
- Karras, T.; Aittala, M.; Laine, S.; Härkönen, E.; Hellsten, J.; Lehtinen, J.; Aila, T. Alias-free generative adversarial networks. Adv. Neural Inf. Process. Syst. 2021, 34, 852–863. [Google Scholar]
- Banerjee, S.; Bernhard, J.S.; Scheirer, W.J.; Bowyer, K.W.; Flynn, P.J. SREFI: Synthesis of realistic example face images. In Proceedings of the IEEE International Joint Conference on Biometrics, Denver, CO, USA, 1–4 October 2017; pp. 37–45. [Google Scholar] [CrossRef] [Green Version]
- Mishra, S.; Shukla, A.K.; Muhuri, P.K. Explainable Fuzzy AI Challenge 2022: Winner’s Approach to a Computationally Efficient and Explainable Solution. Axioms 2022, 11, 489. [Google Scholar] [CrossRef]
- Adadi, A.; Berrada, M. Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI). IEEE Access 2018, 6, 52138–52160. [Google Scholar] [CrossRef]
- Das, A.; Rad, P. Opportunities and challenges in explainable artificial intelligence (xai): A survey. ar**v 2020, ar**v:2006.11371. [Google Scholar]
Study | Approach | Dataset | Performance | Source Code | Year |
---|---|---|---|---|---|
Deepfake Generation | |||||
Wang et al. [55] | Real-time face swap** using CANDIDE-3 | COFW [132], 300W [133], LFW [134] | SWR = 87.9%. | × | 2018 |
Natsume et al. [56] | Face swap** and editing using RSGAN | CelebA [135] | MS-SSIM = 0.087 | × | 2018 |
Chen et al. [61] | High fidelity encoder-decoder | VGGFace2 [136] | Qualitative Analysis | https://github.com/neuralchen/SimSwap (accessed on 4 January 2023) | 2021 |
Xu et al. [137] | Lightweight Identity-aware Dynamic Network | VGGFace2 [136] FaceForensics++ [90] | FID = 6.79% | https://github.com/Seanseattle/MobileFaceSwap (accessed on 4 January 2023) | 2022 |
Shu et al. [138] | Portrait, identity, and pose encoders with generator and feature pyramid network | VoxCeleb2 [139] | PSNR = 33.26 | https://github.com/jmliu88/heser (accessed on 4 January 2023) | 2022 |
Deepfake Detection | |||||
Afcha et al. [140] | CNNs | FaceForensics++ [90] | Acc = 98.40% | https://github.com/DariusAf/MesoNet (accessed on 4 January 2023) | 2018 |
Zhao et al. [77] | Multi-attentional | FaceForensics++ [90] DFDC [3] | Acc = 97.60% LL = 0.1679 | https://github.com/yoctta/multiple-attention (accessed on 4 January 2023) | 2021 |
Miao et al. [141] | Transformers via bag-of-feature for generalization | FaceForensics++ [90], Celeb-DF [142], DeeperForensics-1.0 [143] | Acc = 87.86% AUC = 82.52% Acc = 97.01% | × | 2021 |
Prajapati et al. [144] | Perceptual Image Assessment + GANs | DFDC [3] | AUC = 95% Acc = 91% | https://github.com/pratikpv/mri_gan_deepfake (accessed on 4 January 2023) | 2022 |
Wang et al. [75] | Multi-modal Multi-scale Transformer (M2TR) | FaceForensics++ [90] | Acc = 97.93% | https://github.com/wangjk666/M2TR-Multi-modal-Multi-scale-Transformers-for-Deepfake-Detection (accessed on 4 January 2023) | 2022 |
Reenactment Generation | |||||
Zhang et al. [145] | Decoder + war** | CelebA-HQ [146] FFHQ [147] RAF-DB [148] | AU = 75.1% AU = 70.9% AU = 71.1% | https://github.com/bj80heyue/One_Shot_Face_Reenactment (accessed on 4 January 2023) | 2019 |
Ngo et al. [149] | Encoder-decoder | 300VW [150] | CL= 1.46 | × | 2020 |
Tripathy et al. [151] | Facial attribute controllable GANs | FaceForensics++ [90] | CSIM = 0.747 | × | 2021 |
Bounareli et al. [152] | 3D shape model | VoxCeleb [153] | FID = 0.66 | × | 2022 |
Agarwal et al. [154] | Audio-Visual Face Reenactment GAN | VoxCeleb [153] | FID = 9.05 | https://github.com/mdv3101/AVFR-Gan/ (accessed on 4 January 2023) | 2023 |
Reenactment Detection | |||||
Nguyen et al. [155] | Autoencoder | FaceForensics++ [90] | EER = 7.07% | https://github.com/nii-yamagishilab/ClassNSeg (accessed on 4 January 2023) | 2019 |
Dang et al. [156] | CNNs + Attention mechanism | FaceForensics++ [90] | AUC = 99.4% EER = 3.4% | https://github.com/Jstehouwer/FFD_CVPR2020 (accessed on 4 January 2023) | 2020 |
Kim et al. [157] | Knowledge Distillation | FaceForensics++ [90] | Acc = 86.97% | × | 2021 |
Yu et al. [158] | U-Net Structure | FaceForensics++ [90] | Acc = 97.26% | × | 2022 |
Wu et al. [159] | Multistream Vision Transformer Network | FaceForensics++ [90] | Acc = 94.46% | × | 2022 |
Attribute Manipulation Generation | |||||
Lample et al. [160] | Encoder-decoder | CelebA [135] | RMSE = 0.0009 | https://github.com/facebookresearch/FaderNetworks (accessed on 4 January 2023) | 2018 |
Liu et al. [161] | Selective transfer GANs | CelebA [135] | Acc = 70.80% | https://github.com/csmliu/STGAN (accessed on 4 January 2023) | 2019 |
Kim et al. [162] | Real-time style map GANs | CelebA-HQ [146] AFHQ [163] | FID = 4.03 FID = 6.71 | https://github.com/naver-ai/StyleMapGAN (accessed on 4 January 2023) | 2021 |
Huang et al. [164] | Multi-head encoder and decoder | CelebA-HQ [146] StyleMapGAN [162] | MSE = 0.023 FID = 7.550 | × | 2022 |
Sun et al. [165] | 3D-aware generator with two decoupled latent codes | FFHQ [147] | FID = 28.2 | https://github.com/MrTornado24/FENeRF (accessed on 4 January 2023) | 2022 |
Attribute Manipulation Detection | |||||
Wang et al. [166] | CNNs | Own dataset | Acc = 90.0% | https://github.com/peterwang512/FALdetector (accessed on 4 January 2023) | 2019 |
Du et al. [167] | DFT + CNNs | Deepfake-in-the-wild [168] Celeb-DF [142] DFDC [3] | Acc = 78.00% Acc = 96.00% Acc = 81.00% | × | 2020 |
Akhtar et al. [36] | DNNs | Own dataset | Acc = 99.31 | × | 2021 |
Rathgeb et al. [169] | Human majority voting | FERET [170] | CCR = 62.8% | × | 2022 |
Guo et al. [171] | Gradient operator convolutional network with tensor pre-processing and manipulation trace attention module | FaceForensics++ [90] | Acc = 94.86% | https://github.com/EricGzq/GocNet-pytorch (accessed on 4 January 2023) | 2023 |
Entire face synthesis generation | |||||
Li et al. [172] | Conditional self-attention GANs | CelebA-HQ [146] | KID = 0.62 | https://github.com/LiYuhangUSTC/Lines2Face (accessed on 4 January 2023) | 2019 |
Karras et al. [81] | StyleGAN | FFHQ [147] | FID = 3.31 | https://github.com/NVlabs/stylegan2 (accessed on 4 January 2023) | 2020 |
**a et al. [173] | Textual descriptions GANs | CelebA-HQ [146] | FID = 106.37 | https://github.com/IIGROUP/TediGAN (accessed on 4 January 2023) | 2021 |
Song et al. [174] | Text-to-speech system | LibriTTS dataset [175] AISHELL-3 [176] | FPS = 30.3 | × | 2022 |
Li et al. [177] | StyleT2I: High-Fidelity Text-to-Image Synthesis | CelebA-HQ [146] | FID = 18.02 | https://github.com/zhihengli-UR/StyleT2I (accessed on 4 January 2023) | 2022 |
Entire face synthesis detection | |||||
Wang et al. [178] | CNNs | StyleGAN2 [81] ProGAN [146] | AP = 99.10% AP = 100% | https://github.com/peterwang512/CNNDetection (accessed on 4 January 2023) | 2020 |
Pu et al. [179] | Incremental clustering | PGGAN [146] | F1 Score = 99.09% | https://github.com/jmpu/NoiseScope (accessed on 4 January 2023) | 2020 |
Yousaf et al. [180] | Two-Stream CNNs | StarGAN [101] | Acc = 96.32% | × | 2021 |
Nowroozi et al. [181] | Cross-band and spatial co-occurrence matrix + CNNs | StyleGAN2 [81] VIPPrint [182] | Acc = 93.80% Acc = 92.56% | × | 2022 |
Boyd et al. [183] | Human-annotated saliency maps into a deep learning loss function | StyleGAN2 [81], ProGAN [146], StyleGAN [147], StyleGAN2-ADA [184], StyleGAN3 [185], StarGANv2 [163], SREFI [186] | AUC = 0.633 | https://github.com/BoydAidan/CYBORG-Loss (accessed on 4 January 2023) | 2023 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the author. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Akhtar, Z. Deepfakes Generation and Detection: A Short Survey. J. Imaging 2023, 9, 18. https://doi.org/10.3390/jimaging9010018
Akhtar Z. Deepfakes Generation and Detection: A Short Survey. Journal of Imaging. 2023; 9(1):18. https://doi.org/10.3390/jimaging9010018
Chicago/Turabian StyleAkhtar, Zahid. 2023. "Deepfakes Generation and Detection: A Short Survey" Journal of Imaging 9, no. 1: 18. https://doi.org/10.3390/jimaging9010018