Deepfake detection using machine learning

Chapke, Nilima and Kumawat, Pratik and Swami, Shravani and Sridhar, Tejasa (2025) Deepfake detection using machine learning. World Journal of Advanced Engineering Technology and Sciences, 15 (2). pp. 332-339. ISSN 2582-8266

The evolution of artificial intelligence (AI), machine learning (ML), and deep learning (DL) sophistication has escalated the ways multimedia tools can be altered. AI’s impacts come as pros and cons. One of the major worries is deepfakes that are images, videos, or audio files made with generative adversarial networks (GANs) which can wrongly impersonate a person's identity. Some of the dangerous malicious abuses of deepfakes include violation of privacy, terrorism, political sabotage, blackmail, and invasion of sovereignty. Scientists utilize neural networks and deep learning to solve these problems. Those working in healthcare, analytics, and even in computer vision branch make use of AI for disease diagnosis and pattern detection in big data. However, the potential for abuse creates the need for effective detection systems, ethical regulations, and policies around AI powered digital forgery. It is necessary to implement appropriate policy frameworks and advance the management of AI in such a manner that the risks arising from deepfakes are significantly mitigated while control of the technology is thoroughly maintained.