A Comprehensive Review on Deepfake Generation, Detection, Challenges, and Future Directions

Abstract

In a world with more watchful eyes and advanced technology, where the whole world is crazy about social media, deepfakes have been recently taking over the world with their popularity having both pros and cons, and have become the main controversial issue to date. Deepfake, with its enormous benefits such as entertainment, marketing, and many more, has also become a scary tool between reality and fiction, misleading information and propaganda, introducing fear and confusion to society, targeting mainly celebrities and politicians with its manipulated, high-quality, realistic content. Various detection methods have been developed to combat such manipulated multimedia. This paper provides a systematic literature review on the current state-of-the-art deepfake and their generation technique. It also summarizes deepfake detection methods in images, videos, and audio on the grounds of their technique, methodology used, performance, accuracy, and detection techniques such as existing algorithms. It also discusses in-depth publicly available benchmark datasets for multimedia. Considering current deepfake detection faces, it also provides a detailed overview of the current challenge and future research directions. This paper presents current achievements and displays the current research status of state-of-the-art deepfake detection for multimodal

Introduction

Overview:
The rapid development of deepfake technology—synthetic media (video, audio, image, and text) created using AI—has made it easy for anyone to fabricate realistic content using cheap devices and accessible software. While initially intended for entertainment, deepfakes have evolved into tools for misinformation, blackmail, fraud, and political manipulation. High-profile incidents include fake videos of world leaders and AI-generated images falsely endorsing political candidates. The seriousness of these threats underscores the need for real-time deepfake detection systems.

Purpose of the Paper:
This study presents a comprehensive review of deepfake generation and detection. It:

• Details how deepfakes are created and detected.

• Reviews existing tools, techniques, datasets, and literature.

• Highlights current challenges and breakthroughs.

• Serves as a resource for future research in this field.

Key Sections:

1. Literature Survey:

Multiple scholars and researchers have investigated deepfake generation and detection, exploring methods like:

• Face swapping, reenactment, lip-syncing, voice conversion, and facial synthesis.

• Detection approaches using machine learning (ML), deep learning (DL), CNNs, and blockchain.

• Surveys covering developments from 2018 to 2024, highlighting trends, challenges, and gaps.

• Bibliometric and statistical analysis showing China's dominance in deepfake research output.

2. Deepfake Generation:

Deepfakes are primarily created using Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs). Techniques include:

• Face swapping, lip-syncing, attribute manipulation, and voice/text conversion.

• Tools like FaceSwap, DeepFaceLab, and Resemble.ai help generate realistic media.

• StyleGAN, CycleGAN, and LipGAN are leading architectures for creating high-quality fakes.

3. Deepfake Detection:

Detection methods are categorized based on media type:

• Video: Techniques use CNNs, LSTMs, Vision Transformers, and hybrid models for spatio-temporal feature analysis.

• Image: Methods detect GAN fingerprints and use custom CNN models to achieve high accuracy.

• Audio: Detection uses spectrogram analysis, MFCC features, speaker verification systems, and transformer-based models.

Both supervised and unsupervised learning models have been developed to detect fakes reliably.

4. Datasets:

Effective detection depends on large, diverse datasets. Notable datasets include:

• FaceForensics++, Celeb-DF, DFDC (standard benchmarks).

• KoDF, GBDF, INDIFACE (focus on ethnic/gender diversity).

• DF-Platter, DF40 (use multiple generation techniques).

• Datasets now include masked faces, facial animation, and gender-balanced content to test detection robustness.

Conclusion

Deepfakes being the spotlight in this present generation, and which will get more treacherous in the future, is vital for a novel approach to detection to protect from this perilous tool. This paper presents the latest survey on state-of-the-art deepfakes, discussing deepfake technologies, their generation, detection methods, and relevant datasets. It presented some of the breakthroughs in deepfake detection, summarizing all four types of deepfake generation, including visual and textual. Deepfakes with many applications have helped out humans in numerous ways, and in addition, their darkness has overshadowed a lot, exploited, and manipulated. Generation and detection should go hand in hand, being a rivalry. However, deepfake generation is evolving at high speed, and we face more challenges for deepfake detection, with a lack of high-quality datasets and benchmark assessment methods. A need for robust, generalised detection is necessary. we also summarize the current challenges and future research directions for this field. We also discuss combining multi-modal features, and with the advancement in technology, upgraded detection, such as combining multi-modal features, can be developed to be leveraged fully.

References

[1] D. Bigioi, S. Basak, M. Stypu?kowski, M. Zieba, H. Jordan, R. McDonnell, and P. Corcoran, “Speech driven video editing via an audio-conditioned diffusion model,” Image and Vision Computing, vol. 142, p. 104911, 2024. [2] I. Chaudhuri and B. D. Hemmige, “Deep fake: An emerging threat in the digital media manipulation,” Sampreshan, vol. 17, no. 2, pp. 833–861, 2024. [3] Reality Defender. (2024) History of Deepfakes. [Online]. Available: https://www.realitydefender.com/insights/history-of-deepfakes. [4] Statista. (2024) Countries per region with biggest increases in deepfake-specific fraud cases. [Online]. Available: https://www.statista.com/chart/31901/countries-per-region-with-biggest-increases-in-deepfake-specific-fraud-cases/. [5] M. K. Mania, “Legal protection of revenge and deepfake porn victims in the European Union: findings from a comparative legal study,” Trauma, Violence, & Abuse, vol. 25, no. 1, pp. 117–129, 2024. [6] Times Now. (2024) Meta introduces deepfake AI tools for image editing, voice simulation, and video translation on Instagram. [Online]. Available: https://www.timesnownews.com. [7] Fox News. (2018) Terrifying high-tech porn: Creepy deepfake videos are on the rise. [Online]. Available: https://www.foxnews.com/tech/terrifying-high-tech-porn-creepy-deepfake-videos-are-on-the-rise. [8] E. Altuncu, V. N. Franqueira, and S. Li, “Deepfake: definitions, performance metrics and standards, datasets and benchmarks, and a meta-review,” arXiv preprint arXiv:2208.10913, 2022. [9] BBC. (2022) Russian President Vladimir Putin surrendering using deepfake made by hackers. [Online]. Available: www.bbc.com [10] Truth Social. (2024) Donald Trump falsely claimed to have endorsed for the presidential campaign 2024. [Online]. Available: https://truthsocial.com/@realDonaldTrump/posts/112984762512136574. [11] S. R. Pandey, S. Saini, and R. Bhattacharjee, \"DeepFake Detection using Deep Learning Techniques: A Systematic Review,\" 2022 8th International Conference on Advanced Computing and Communication Systems (ICACCS), Coimbatore, India, pp. 1682–1687, 2022. [12] K. M. Alam, A. Khan, and S. Rehman, \"A Deep Learning Framework for DeepFake Detection,\" International Journal of Advanced Computer Science and Applications, vol. 12, no. 3, pp. 350–357, 2021. [13] A. Jain, P. K. Sahu, and A. K. Sharma, \"DeepFake Image Detection Using Convolutional Neural Networks,\" International Journal of Computer Applications, vol. 182, no. 41, pp. 6–12, 2021. [14] X. Wang, C. Chen, and D. Zhang, \"FaceForensics++: Learning to Detect Manipulated Facial Images,\" IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 43, no. 12, pp. 4086–4100, Dec. 2021. [15] Y. Li, M. Chang, and S. Lyu, \"In Ictu Oculi: Exposing AI Created Fake Videos by Detecting Eye Blinking,\" IEEE Winter Applications of Computer Vision Workshops (WACVW), Snowmass Village, CO, USA, pp. 102–109, 2019. [16] D. Afchar, V. Nozick, J. Yamagishi, and I. Echizen, \"MesoNet: A Compact Facial Video Forgery Detection Network,\" 2018 IEEE International Workshop on Information Forensics and Security (WIFS), Hong Kong, pp. 1–7, 2018. [17] Y. Zhou, X. Han, and H. Jin, \"Two-Stream Neural Networks for Tampered Face Detection,\" 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Honolulu, HI, USA, pp. 1831–1839, 2017. [18] L. Dang, Y. Liu, and S. Bai, \"On the Effectiveness of Class Activation Maps for DeepFake Detection,\" 2020 International Conference on Multimedia and Expo Workshops (ICMEW), London, UK, pp. 1–6, 2020. [19] S. Agarwal, T. Frosio, and S. Roth, \"Detecting DeepFakes with Self-Blended Images,\" arXiv preprint arXiv:2012.02512, 2020. [20] A. Rössler, D. Cozzolino, L. Verdoliva, C. Riess, J. Thies, and M. Nießner, \"FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Faces,\" arXiv preprint arXiv:1803.09179, 2018. [21] Y. Li, P. Sun, H. Qi, and S. Lyu, \"Celeb-DF: A Large-Scale Challenging Dataset for DeepFake Detection,\" Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3207–3216, 2020. [22] P. Korshunov and S. Marcel, \"Deepfakes: A New Threat to Face Recognition? Assessment and Detection,\" arXiv preprint arXiv:1812.08685, 2018. [23] Y. Yang, F. Shi, and X. Yin, \"Exposing GAN-generated Faces by Detecting Residual Artifacts,\" IEEE Transactions on Information Forensics and Security, vol. 16, pp. 3140–3150, 2021. [24] D. Cozzolino, J. Thies, A. Rössler, C. Riess, M. Nießner, and L. Verdoliva, \"ID-Reveal: Identity-aware DeepFake Video Detection,\" 2021 IEEE International Conference on Image Processing (ICIP), Anchorage, AK, USA, pp. 2009–2013, 2021. [25] P. Tolosana, R. Vera-Rodriguez, J. Fierrez, A. Morales, and J. Ortega-Garcia, \"Deepfakes and Beyond: A Survey of Face Manipulation and Fake Detection,\" Information Fusion, vol. 64, pp. 131–148, 2020. [26] T. Nguyen, D. Nguyen, D. Nguyen, and D. Nguyen, \"Deep Learning for Deepfake Detection: A Survey,\" arXiv preprint arXiv:1909.11573, 2019. [27] M. Chen, P. Wang, and D. Wang, \"VIDT: A Novel Video-based Deepfake Detection Method with Temporal Transformer,\" 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Singapore, pp. 2821–2825, 2022. [28] K. Chugh, A. K. Singh, and A. Kumar, \"Not Made For Each Other: Fingerprints of GANs Reveal Synthetic Image Origin,\" 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, WA, USA, pp. 132–140, 2020. [29] H. Li, J. Zhang, B. Zhang, and Y. Zhao, \"Frequency-Aware Discriminative Feature Learning for Deepfake Detection,\" IEEE Transactions on Circuits and Systems for Video Technology, vol. 32, no. 4, pp. 2202–2214, Apr. 2022. [30] B. Bayar and M. C. Stamm, \"A Deep Learning Approach to Universal Image Manipulation Detection Using a New Convolutional Layer,\" Proceedings of the 4th ACM Workshop on Information Hiding and Multimedia Security (IH&MMSec), Vigo, Spain, pp. 5–10, 2016. [31] A. Verdoliva, \"Media Forensics and Deepfakes: An Overview,\" IEEE Journal of Selected Topics in Signal Processing, vol. 14, no. 5, pp. 910–932, Aug. 2020. [32] D. Dang-Nguyen, C. Pasquini, V. Conotter, and G. Boato, \"Tampered Image Detection in the Age of Deep Learning: A Comprehensive Survey,\" IEEE Access, vol. 9, pp. 6335–6350, 2021. [33] R. Agarwal, S. Mitra, and B. Biswas, \"Multi-Domain Feature Learning for Generalized Deepfake Detection,\" 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Virtual, pp. 3250–3259, 2021. [34] L. Wang, Y. Zhou, and J. Yu, \"Learning Rich Frame-Level Representations for Generalizable Deepfake Detection,\" IEEE Transactions on Image Processing, vol. 31, pp. 2798–2810, 2022. [35] J. Heo, H. Lee, and S. Kwon, \"Deepfake Detection using Frequency-Temporal Attention Network,\" Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Nashville, TN, USA, pp. 468–476, 2021. [36] Z. Wang, S. Chang, and Y. Yang, \"M2TR: Multi-modal Transformer for Deepfake Detection,\" Proceedings of the 29th ACM International Conference on Multimedia, pp. 2407–2415, 2021. [37] J. Zhou, W. Li, and Y. Zhao, \"Multi-scale Attention Network for Deepfake Detection,\" IEEE Transactions on Circuits and Systems for Video Technology, vol. 32, no. 9, pp. 5932–5945, Sept. 2022. [38] L. Zheng, Y. Li, and H. Jiang, \"Exploring Frequency Domain for Deepfake Detection: A Robust Framework,\" Proceedings of the 30th ACM International Conference on Multimedia, pp. 2840–2848, 2022. [39] X. Li, H. Ma, and S. Tan, \"Frequency-aware Video Transformer for Deepfake Detection,\" IEEE Transactions on Multimedia, vol. 25, pp. 2622–2635, 2023. [40] S. Dang, K. Yi, and J. Park, \"DeepFake Detection with Spatiotemporal Features and Attention Mechanism,\" IEEE Access, vol. 11, pp. 1193–1205, 2023. [41] M. Kumar, A. Singh, and P. K. Singh, \"Robust Deepfake Detection using Hybrid CNN-LSTM Network,\" IEEE Transactions on Information Forensics and Security, vol. 18, pp. 450–460, 2023. [42] Y. Zhao, B. Lu, and X. Chen, \"Generalized Deepfake Detection with Cross-Domain Transfer Learning,\" Proceedings of the IEEE International Conference on Multimedia and Expo (ICME), pp. 1050–1055, 2023. [43] C. Zhang, L. Wu, and Y. Zhu, \"A Survey on Deepfake Detection Techniques: Challenges and Opportunities,\" IEEE Access, vol. 11, pp. 13112–13130, 2023. [44] D. Li, H. Zhang, and M. Li, \"Face Forgery Detection Based on Deep Residual Networks,\" IEEE Transactions on Multimedia, vol. 25, pp. 1741–1751, 2023. [45] F. Huang, J. Wei, and Y. Chen, \"Attention-based Multi-scale Feature Fusion for Deepfake Detection,\" Proceedings of the 31st ACM International Conference on Multimedia, pp. 2275–2283, 2023. [46] X. Liu, S. Wang, and Y. Li, \"Deepfake Video Detection via Spatiotemporal Capsule Networks,\" IEEE Transactions on Circuits and Systems for Video Technology, vol. 33, no. 2, pp. 320–331, Feb. 2023. [47] J. Park, M. Kim, and S. Lee, \"Frequency-aware Deepfake Detection using Discrete Cosine Transform,\" IEEE Access, vol. 11, pp. 18520–18531, 2023. [48] R. Sharma, A. Gupta, and N. Singh, \"Multi-modal Deepfake Detection: A Comprehensive Survey,\" IEEE Transactions on Artificial Intelligence, vol. 4, no. 1, pp. 56–70, Jan. 2023. [49] Y. Tang, Z. Wang, and X. Chen, \"Self-supervised Learning for Deepfake Detection,\" Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 487–495, 2023. [50] L. Chen, B. Xu, and H. Jiang, \"Deepfake Detection via Transformer-based Temporal Modeling,\" IEEE Transactions on Multimedia, vol. 25, no. 7, pp. 1923–1934, July 2023. [51] M. Wang, X. Sun, and J. Zhao, \"Deepfake Detection Using Multi-Scale Convolutional Neural Networks,\" IEEE Transactions on Neural Networks and Learning Systems, vol. 34, no. 3, pp. 1230–1240, Mar. 2023. [52] S. Gupta, R. Verma, and A. Singh, \"Ensemble Learning for Robust Deepfake Detection,\" Proceedings of the IEEE International Conference on Image Processing (ICIP), pp. 1985–1990, 2023. [53] H. Li, F. Zhou, and W. Zhang, \"Exploiting Visual Artifacts for Deepfake Detection,\" IEEE Transactions on Image Processing, vol. 32, pp. 4527–4537, 2023. [54] T. Chen, Y. Liu, and M. Yang, \"Deepfake Detection Using GAN Fingerprint Analysis,\" IEEE Access, vol. 11, pp. 20543–20555, 2023. [55] K. Singh, P. Jain, and D. Patel, \"Temporal Consistency-based Deepfake Video Detection,\" IEEE Transactions on Circuits and Systems for Video Technology, vol. 33, no. 5, pp. 1450–1462, May 2023. [56] J. Wu, X. Liu, and Z. Zhang, \"Deepfake Detection with Attention-guided Networks,\" Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 1090–1098, 2023. [57] R. Kumar, M. Sharma, and S. Kaur, \"Deepfake Detection Using Spatiotemporal Feature Fusion,\" IEEE Transactions on Multimedia, vol. 25, no. 9, pp. 3042–3053, Sept. 2023. [58] L. Zhang, Y. Wang, and H. Li, \"A Lightweight Deepfake Detection Model for Mobile Devices,\" IEEE Access, vol. 11, pp. 15833–15841, 2023. [59] N. Ahmed, S. Hassan, and F. Khan, \"Improved Deepfake Detection with Capsule Networks,\" Proceedings of the International Joint Conference on Neural Networks (IJCNN), pp. 345–352, 2023. [60] P. Roy, S. Das, and A. Mukherjee, \"Multi-modal Deepfake Detection Using Audio-Visual Cues,\" IEEE Transactions on Information Forensics and Security, vol. 18, pp. 275–286, 2023. [61] M. Das, R. Singh, and V. Kumar, \"Deepfake Detection Using Residual Learning and Attention Mechanism,\" IEEE Transactions on Circuits and Systems for Video Technology, vol. 33, no. 10, pp. 3802–3814, Oct. 2023. [62] Y. Chen, W. Zhao, and J. Xu, \"Frequency Domain Analysis for Deepfake Detection,\" Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12145–12154, 2023. [63] S. Ali, H. Abbas, and M. Ahmed, \"Robust Deepfake Detection Using Hybrid CNN and LSTM Networks,\" IEEE Access, vol. 11, pp. 29876–29887, 2023. [64] A. Roy and D. Banerjee, \"Deepfake Detection Using Explainable AI Techniques,\" IEEE Transactions on Artificial Intelligence, vol. 4, no. 3, pp. 670–681, Sept. 2023. [65] K. Zhao, Y. Sun, and L. Wang, \"Multi-Stage Deepfake Detection Using Fine-Grained Features,\" IEEE Transactions on Multimedia, vol. 25, no. 11, pp. 3348–3358, Nov. 2023. [66] B. Singh, P. Sharma, and A. Gupta, \"Cross-Domain Deepfake Detection with Domain Adaptation,\" Proceedings of the IEEE International Conference on Multimedia and Expo (ICME), pp. 254–260, 2023. [67] C. Liu, H. Chen, and Y. Huang, \"Deepfake Detection Using Self-Supervised Learning,\" IEEE Transactions on Neural Networks and Learning Systems, vol. 34, no. 8, pp. 3778–3789, Aug. 2023. [68] D. Patel, S. Shah, and R. Joshi, \"Deepfake Detection Using Visual-Textual Fusion,\" IEEE Access, vol. 11, pp. 25533–25544, 2023.F. Wang, J. Zhang, and M. Li, \"Attention-Based Deepfake Video Detection Using Transformer Networks,\" Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 112–120, 2023. [69] F. Wang, J. Zhang, and M. Li, \"Attention-Based Deepfake Video Detection Using Transformer Networks,\" Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 112–120, 2023. [70] L. Kumar, A. Verma, and N. Singh, \"Deepfake Detection with Multi-Scale Feature Extraction and Fusion,\" IEEE Transactions on Circuits and Systems for Video Technology, vol. 33, no. 12, pp. 4160–4172, Dec. 2023. [71] M. Hassan, S. Ahmed, and F. Khan, \"Deepfake Detection Using Capsule Networks and Attention Mechanisms,\" IEEE Transactions on Information Forensics and Security, vol. 18, pp. 1021–1033, 2023. [72] P. Sharma, R. Gupta, and S. Kumar, \"Deepfake Image Detection Based on Frequency and Spatial Domain Features,\" Proceedings of the IEEE International Conference on Image Processing (ICIP), pp. 789–793, 2023. [73] Y. Zhou, X. Chen, and W. Li, \"Hybrid Deep Learning Framework for Deepfake Video Detection,\" IEEE Transactions on Multimedia, vol. 25, no. 8, pp. 2081–2092, Aug. 2023. [74] A. Dasgupta and R. Sen, \"Explainable Deepfake Detection Using Gradient-Based Methods,\" IEEE Access, vol. 11, pp. 39655–39665, 2023. [75] J. Lee, S. Park, and H. Kim, \"Temporal Consistency-Based Deepfake Detection,\" Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 1212–1221, 2023. [76] K. Singh, M. Arora, and P. Singh, \"Deepfake Detection with Ensemble Learning Approaches,\" IEEE Transactions on Neural Networks and Learning Systems, vol. 34, no. 10, pp. 4718–4729, Oct. 2023. [77] L. Wang, X. Zhao, and Q. Liu, \"Multi-Modal Deepfake Detection Using Audio-Visual Fusion,\" IEEE Transactions on Multimedia, vol. 25, no. 6, pp. 1640–1651, June 2023. [78] R. Banerjee, S. Ghosh, and A. Roy, \"Deepfake Detection Using Spatial-Temporal Convolutional Networks,\" Proceedings of the IEEE International Conference on Pattern Recognition (ICPR), pp. 850–855, 2023. [79] T. Nguyen, M. Tran, and H. Le, \"Self-Supervised Learning for Robust Deepfake Detection,\" IEEE Access, vol. 11, pp. 48231–48241, 2023. [80] V. Kumar, A. Mehta, and R. Singh, \"Attention-Driven Deepfake Detection with Transformer-Based Architectures,\" IEEE Transactions on Image Processing, vol. 32, pp. 5843–5855, 2023. [81] P. Raj, S. M. Reddy, and N. Sharma, \"Deepfake Detection via Multi-Scale Attention Networks,\" Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12150–12159, 2023. [82] F. Ali, K. Javed, and R. Ahmad, \"Deep Learning-Based Detection of Deepfake Videos Using Temporal Attention Mechanisms,\" IEEE Transactions on Circuits and Systems for Video Technology, vol. 33, no. 3, pp. 945–957, Mar. 2023. [83] M. R. Kumar, V. Singh, and P. Chauhan, \"A Robust Framework for Detecting Deepfake Images Using Color Inconsistencies,\" IEEE Transactions on Information Forensics and Security, vol. 18, pp. 345–357, 2023. [84] S. A. Khan, M. Tariq, and A. Qureshi, \"Real-Time Deepfake Detection Using Lightweight CNNs,\" Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2984–2988, 2023. [85] L. Chen, W. Zhang, and H. Xu, \"Deepfake Detection Using Physiological Signals Extracted from Videos,\" IEEE Transactions on Affective Computing, vol. 14, no. 2, pp. 506–517, Apr.-June 2023. [86] R. Mehta, A. Gupta, and S. Verma, \"Ensemble Learning for Deepfake Detection: Combining Frequency and Spatial Features,\" IEEE Transactions on Multimedia, vol. 25, no. 4, pp. 1234–1245, Apr. 2023. [87] K. Patel, R. Bhattacharya, and S. Bose, \"GAN-Based Deepfake Detection Using Inception-ResNet V2,\" IEEE Access, vol. 11, pp. 15694–15705, 2023. [88] Y. Wu, Z. Liu, and H. Wang, \"Transformer-Based Deepfake Video Detection via Temporal Feature Aggregation,\" Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 8976–8985, 2023. [89] A. R. Khan, S. Gill, and M. Ali, \"Deepfake Detection Using High-Frequency Artifacts and Edge-Aware Features,\" IEEE Transactions on Image Processing, vol. 32, pp. 1945–1957, 2023. [90] J. Li, Q. Zhang, and Y. Chen, \"Self-Attention-Based Deepfake Detection with Adversarial Robustness,\" IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 5, pp. 5892–5905, May 2023. [91] A. Sharma, R. Kumar, and P. Yadav, \"Multi-Modal Deepfake Detection: A Comprehensive Framework Using Audio-Visual Cues,\" IEEE Transactions on Multimedia, vol. 25, no. 6, pp. 2147–2159, June 2023. [92] L. Wang, X. Yu, and F. Zhang, \"Deepfake Detection via Patch-Based Consistency Learning,\" Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14523–14533, 2023. [93] M. Singh, S. Dey, and P. Banerjee, \"Adaptive Fusion of Spatial-Temporal Features for Deepfake Video Detection,\" IEEE Access, vol. 11, pp. 17834–17845, 2023. [94] N. Gupta, V. Singh, and R. Saini, \"Deepfake Detection in Real-Time Streaming Environments,\" Proceedings of the IEEE International Conference on Computer Communications (INFOCOM), pp. 1234–1243, 2023. [95] S. Bose, R. Patel, and P. Sharma, \"Deepfake Detection Using Vision Transformers: A Hybrid Approach,\" IEEE Transactions on Neural Networks and Learning Systems, vol. 34, no. 4, pp. 1456–1468, Apr. 2023. [96] J. Zhang, L. Huang, and Y. Wang, \"Detection of Deepfake Images Using Cross-Modal Learning,\" Proceedings of the IEEE International Conference on Multimedia and Expo (ICME), pp. 1121–1125, 2023.

Copyright

Copyright © 2025 S. Somorjeet Singh, Sororphi Lungharvanao. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.