Deepfake technology uses artificial intelligence to create realistic but false audio, images, and videos. Deepfake technology poses a significant threat to the authenticity of visual content, particularly in live-stream scenarios where the immediacy of detection is crucial. Existing Deepfake detection approaches have limitations and challenges, prompting the need for more robust and accurate solutions. This research proposes an innovative approach: combining eye movement analysis with a hybrid deep learning model to address the need for real-time Deepfake detection. The proposed hybrid deep learning model integrates two deep neural network architectures, MesoNet4 and ResNet101, to leverage their respective architectures’ strengths for effective Deepfake classification. MesoNet4 is a lightweight CNN model designed explicitly to detect subtle manipulations in facial images. At the same time, ResNet101 handles complex visual data and robust feature extraction. Combining the localized feature learning of MesoNet4 with the deeper, more comprehensive feature representations of ResNet101, our robust hybrid model achieves enhanced performance in distinguishing between manipulated and authentic videos, which cannot be conducted with the naked eye or traditional methods. The model is evaluated on diverse datasets, including FaceForensics++, CelebV1, and CelebV2, demonstrating compelling accuracy results, with the hybrid model attaining an accuracy of 0.9873 on FaceForensics++, 0.9689 on CelebV1, and 0.9790 on CelebV2, showcasing its robustness and potential for real-world deployment in content integrity verification and video forensics applications.

Deepfake detection has become a critical challenge nowadays with the rise of sophisticated generative techniques that manipulate audio-visual data. Existing methods primarily focus on lip movement synchronization using audio and visual features, often relying on local feature extraction with Convolutional Neural Networks (CNNs). In this work, we propose an enhanced multimodal framework that integrates with local and global features for advanced deepfake detection. Our approach extends traditional pipelines by introducing additional visual features such as eye movement and facial regions, combined with audio features to model cross-modal dependencies. While CNNs capture local features, Vision Transformers (ViTs) extract global contextual relationships from both visual and audio modalities. The diffusion models are incorporated as pre-processors to refine noisy data and generate realistic augmentations, ensuring high-quality feature representation. The proposed framework achieves state-of-the-art performance, with accuracy scores of 0.9987, 0.9825, 0.9915, and 0.9812 on the FakeAVCeleb, AV-Deepfake1M, TVIL, and LAV-DF datasets, respectively. These results demonstrate significant improvements over existing methods, highlighting the framework’s superior generalization and robustness in detecting subtle inconsistencies across manipulated audio-visual data.

The rapid advancements in Artificial Intelligence (AI) and deep learning techniques have led to the creation of highly realistic synthetic media known as deepfakes. These manipulated images, videos, and audio pose significant ethical, security, and privacy concerns. To address this issue, we propose a novel Audio–Visual Synchronisation and Fusion Framework (AVSFF) for real-time detection of deepfakes. This approach focuses on fine-grained lip movement analysis by detecting subtle inconsistencies between lip movements and corresponding audio. By integrating visual and audio features using multimodal fusion techniques, AVSFF aims to distinguish between authentic and manipulated media. The proposed framework is evaluated on diverse datasets, including FakeAVCeleb, AV-Deepfake1M, TVIL, and LAV-DF, demonstrating promising results with accuracies of 0.9973, 0.9760, 0.9890, and 0.9786, respectively. This study contributes to the field by providing a robust real-time solution for detecting deepfakes in audio–visual synthetic data, ensuring enhanced detection accuracy and effective generalization across various deepfake manipulations and demographic data.

The extensive use of artificial intelligence (AI) tools in education and their effectiveness and explicability have become an essential area of investigation because of their scope for ethical and fair use. Therefore, this innovative approach proposed a multimodal machine learning and explainable AI (XAI) approach to predict how ChatGPT’s usage impacts students’ academic outcomes, including satisfaction and performance. Three machine learning models, XGBoost, Random Forest, and Support Vector Machine, were used to predict students’ performance and level of satisfaction. The XAI techniques, SHapley Additive exPlanations and Local Interpretable Model-Agnostic Explanations, were used to investigate how models make decisions with ethical standards and ensure models are reliable and fair in their usage. A custom-created dataset, ChatGPT Survey Data, was utilized for the experiment. All three models gave the promised classification, with Support Vector Machine having the highest accuracy at 89% and the receiver operating characteristic curve and the area under this curve (AUC-ROC) at 92%. Random Forest has 87% accuracy and an AUC-ROC of 90%. XGBoost showed the best accuracy with 92% (R2). XAI analysis revealed ChatGPT usage and satisfaction as key predictors of academic performance, advancing AI’s role in education.

The rapid evolution of deepfake technology necessitates detection frameworks capable of leveraging diverse modalities to ensure robust and real-time performance. This research introduces MMDF-Net, a novel multimodal framework for deepfake detection that integrates visual and audio features. MMDF-Net employs MobileNetV2 for lightweight local facial feature extraction and the Swin Transformer to capture global facial relationships, ensuring comprehensive visual representation. The Wav2vec model is used for audio feature extraction to balance visual data, enabling a holistic approach to detection and using the multimodal fusion mechanism to integrate these features, facilitating an accurate and reliable real-time deepfake framework. The proposed MMDF-Net framework achieves impressive performance on the LAV-DF and TVIL datasets, with LAV-DF yielding an accuracy of 97.0% and TVIL achieving 95.5%. Both datasets demonstrate robust detection capabilities, with the model maintaining high precision, recall, and F1-score while processing samples in less than 100ms, explaining the significance of combining visual and audio modalities for efficient and effective deepfake detection.

Urban traffic congestion necessitates innovative monitoring and control solutions. This study leverages UAV footage and deep learning techniques to classify and analyze traffic density levels autonomously. By employing a pre-trained ResN et50 model enhanced with additional layers, the research optimizes traffic density classification using UAV-captured data. A custom dataset of traffic scenarios in Dammam, Saudi Arabia, was developed, incorporating diverse conditions through advanced normalization and data augmentation techniques to improve resilience and robustness. The modified ResN et50 model demonstrated high classification accuracy across varied traffic scenarios, validating its reliability and scalability for real-world applications. Key findings include the superior adaptability of UAV-based monitoring for real-time urban traffic assessment and the enhanced classification precision achieved through model optimization. This research underscores the potential of integrating UAV technology with deep learning to advance urban traffic management and foster more efficient urban planning strategies.