• Prof. Rupali Sharma
• Samiktha Punathil
• Manali Todankar
• Mohini Pillai
• Shruti Dharashiokar

In recent times, deepfake videos, created through advanced deep learning algorithms, have garnered significant attention. This technology enables hyper realistic face manipulations. The internet has seen a proliferation of deepfake videos, predominantly targeting celebrities and politicians due to the extensive online presence of their visual content. These videos often serve the purpose of tarnishing the reputation of public figures and influencing public opinion, posing a substantial threat to societal stability. While the deepfake algorithm itself lacks inherent moral attributes, its widespread application has predominantly been for negative ends. In response to this, various research initiatives have been launched to counteract the potential harm, focusing on the development of detection methods and the establishment of comprehensive benchmarks. This review seeks to outline the current state of research in deepfake video detection, encompassing the generation process, diverse detection methods, and existing benchmarks. It is evident that existing detection techniques still fall short when applied in real-world scenarios. Consequently, future research efforts should prioritize enhancing the generalization and robustness of these methods.

Deepfake, detection, research, face manipulation

"SURVEY ON DETECTION METHODS FOR DEEPFAKE VIDEOS ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 3, page no.b813-b821, March-2024, Available :http://www.jetir.org/papers/JETIR2403194.pdf

"SURVEY ON DETECTION METHODS FOR DEEPFAKE VIDEOS ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 3, page no. ppb813-b821, March-2024, Available at : http://www.jetir.org/papers/JETIR2403194.pdf