Deepfake image detection and classification model using Bayesian deep learning with coronavirus herd immunity optimizer

<p>Deepfake images are combined media constructed from deep learning (DL) methods, usually Generative Adversarial Networks (GANs), to manipulate visual content, often giving rise to convincing and fabricating descriptions of scenes or people. The Bayesian machine learning (ML) model has made crucial strides over the past two decades, illustrating promise in diverse applications. In deepfake images, detection utilizes computer vision (CV) and ML to spot manipulated content by analyzing unique artefacts and patterns. Recent techniques utilize DL to train neural networks to discriminate between real and fake images, improving the fight against digital manipulation and preserving media integrity. These systems can efficiently detect subtle inconsistencies or anomalies specific to deepfake creations by learning from large datasets of both real and deepfake images. This enables the mitigation of fraudulent content and reliable detection in digital media. We introduce a new Coronavirus Herd Immunity Optimizer with a Deep Learning-based Deepfake Image Detection and Classification (CHIODL-DIDC) technique. The CHIODL-DIDC technique aimed to detect and classify the existence of fake images. To accomplish this, the CHIODL-DIDC technique initially used a median filtering (MF) based image filtering approach. Besides, the CHIODL-DIDC technique utilized the MobileNetv2 model for extracting feature vectors. Moreover, the hyperparameter tuning of the MobileNetv2 model was accomplished using the CHIO method. For deepfake image detection, the CHIODL-DIDC technique implements the deep belief network (DBN) model. Finally, the Bayesian optimization algorithm (BOA) was utilized to select the effectual hyperparameter of the DBN model. The CHIODL-DIDC method's empirical analysis was examined using a benchmark fake image dataset. The performance validation of the CHIODL-DIDC technique illustrated a superior accuracy value of 98.16% over other models under $ Acc{u}_{y} $ , $ Pre{c}_{n} $ , $ Rec{a}_{l} $ , $ {F}_{Score} $ , and MCC metrics.</p>