Journal of Intelligent Systems and Internet of Things JISIoT 2690-6791 2769-786X 10.54216/JISIoT https://www.americaspg.com/journals/show/4026 2019 2019 Chitkara University Institute of Engineering and Technology, Chitkara University, Rajpura, Punjab, India Oday Oday Ministry of Higher Education and Scientific Research, Minister Office, Bagdad, Iraq Raghad Tohmas Esfandiyar Ministry of Higher Education and Scientific Research, Minister Office, Bagdad, Iraq Shahad Hussein Jasim Ministry of Education, Wasit Education Directorate, Bagdad, Iraq; Computer Department, College of Education for Pure Sciences, Wasit University, Iraq Oday Ali Hassen Chitkara University Institute of Engineering and Technology, Chitkara University, Rajpura, Punjab, India Neha Sharma College of Engineering, University of Information Technology and Communications, Baghdad, Iraq Ansam A. Abdulhussein This paper offers a comprehensive framework for real or fake image classification based on three classifiers: a Standard Convolutional Neural Network (CNN), an EfficientNetV2 model based on transfer learning, and a re-trained GAN discriminator to address the challenges in deepfake detection. The CNN, with four convolutional blocks and dropout regularization, offers computational efficiency (87.2% accuracy, 15 msimage inference), while EfficientNetV2 utilizes pre-trained ImageNet weights to achieve state-of-the-art performance (94.7% ac-curacy, AUC: 0.98) using hierarchical feature extraction. The fine-tuned and adversarial-pretrained GAN discriminator demonstrates niche strength in the detection of synthetic artifacts (91% recall for GAN-generated fakes). Training used augmented sets (rotation, shifts, and shear) to increase the generalization boost, with loss optimization and early stopping (binary cross-entropy) controlled through validation. Normalized test set validation affirmed EfficientNetV2's capability at balancing recall (94%) with precision (95%), although the GAN discriminator recorded a lead in adversarial resilience. All the models blended, an ensemble model achieved maximum accuracy (96.1%), under complementarities. Computational baselines showed trade-offs EfficientNetV2 accu-racy vs. resource bias (2.5-hour training), the CNN edge-compatibility, and the GAN discriminator arti-fact-sensitive specialization. The work encourages hybrid architectures and ensemble approaches to balance out single-model vulnerabilities, offering a flexible toolkit for deepfake warfare while emphasizing the need for hardware-aware deployment techniques and ongoing adaptation to changing synthetic approaches. 2026 2026 187 204 10.54216/JISIoT.180214 https://www.americaspg.com/articleinfo/18/show/4026