Building the trust: AI-based systematic literature review of deepfake detection across modalities and domains

Artificial Intelligence (AI) based generative models have advanced rapidly, making it possible to generate highly realistic synthetic media. These technologies build new opportunities for creative and legitimate use in various domains, but they also give rise to significant concerns about digital trust and privacy. Though it has various legitimate uses, it can also be used to generate harmful content, often known as "deepfake". It can cause political misinformation, non-consensual content generation and financial fraud that costs millions. These consequences are harmful for democracy, healthcare and the legal system. One of the growing concerns is the emergence of deepfake in medical imaging, where fabrication and manipulation of diagnostic scans and clinical imagery directly threaten patient safety, healthcare integrity and medical forensics. This paper presents a systematic literature review (SLR) of various deepfake generation and detection methods based on Artificial intelligence. Following the PRISMA framework , relevant studies are identified from major scientific databases, including IEEE Xplore, Scopus, ScienceDirect, SpringerLink, Google scholar and ACM Digital Library. Following a PRISMA-based search and screening process, 142 primary studies were selected from an initial pool of studies, based on predefined inclusion, exclusion, and quality-assessment criteria. Some literature published prior to 2021 is additionally cited for contextual background, separate from the 142 primary studies reviewed. The selected literature is analysed and categorised into different deepfake generation and detection methods. Furthermore, benchmark datasets, evaluation protocols and comparative performance trends are analysed. Key challenges such as dataset bias, poor generalization, adversarial vulnerability and lack of explainability are discussed. Future research directions are outlined. This review aims to serve as a useful reference for researchers and practitioners working on reliable deepfake detection systems.