The advancement of open-source frameworks and user-friendly manipulation applications has accelerated the spread of deep fakes. In this study, we proposed optimal features assisted with a dual attention (DA) network strategy to combat this proliferation in consumer imaging devices. We employed EfficientNetV2 (ENV2) as the primary feature extractor, initially utilizing its pre-trained weights from the ImageNet dataset while keeping its layers frozen to leverage their rich feature extraction capabilities. We enhance this base model with a DA module that integrates the Convolutional Block Attention Module (CBAM), which utilizes both channel attention (CA) and spatial attention (SA) mechanisms to improve feature representation. CA dynamically adjusts channel-wise feature responses to capture interdependencies between channels, thereby improving feature discrimination. SA allows the network to focus on important regions within feature maps, enhancing localization and reducing noise. The features are assisted in multi-stages of the network with residual fashion to focus on discriminative visual information. During fine-tuning, we unfreeze the deeper layers of ENV2 for further refinement of learned features to better suit the deepfake dataset. We employed a targeted fine-tuning approach, unfreezing specific layers and applying iterative adjustments to optimize performance, providing valuable insights into countering the growing use of synthetic media in consumer imaging. To validate our network, we conducted comprehensive experiments on four benchmark datasets: FaceForensics++, the World Leaders, Celeb-DF, and DFDC. As a result, our network achieved superior performance compared to existing benchmarks and state-of-the-art approaches, offering a promising solution for robust deepfake detection (DD) in consumer imaging technologies.

The emergence of smart and nanobiosensor (NB) technologies has transformed the monitoring and management of bacterial infections. These developments offer remarkable accuracy and precision for detecting infectious pathogens. Smart artificial intelligence (AI)-assisted and NB-based methods are used as powerful tools in biomedicine for bacterial detection, combatting multidrug resistance, and diagnosing infections. In this study, we delve into the advancements in these technologies, focusing on AI-based techniques for NBs in detecting bacterial infections from 2019 to 2024. We analyze the contributions of machine learning and deep learning techniques to enhance performance and reliability. The new approaches to improve the effectiveness and versatility of antibacterial treatments are critically analyzed. Our study includes the observations of carbon nanoparticles that selectively target bacteria using photothermal properties and the production of hybrid hydrogel composites with capabilities. Furthermore, the study emphasizes the crucial significance of NBs in propelling the progress of diagnostic methods, biosensing technologies, and treatments, thereby transforming the healthcare industry and the way diseases are managed. In addition, we explore pathogen-based infections, bacterial diagnosis, and treatment using engineered NBs enhanced with various modalities such as electrochemistry, acoustics, electromagnetism, and photothermal resonance. Our comprehensive review highlights the potential and throws light on future research directions for effective management and control of bacterial infections.

The rapid expansion of nanotechnology has transformed numerous sectors, with nanoproducts now ubiquitous in everyday life, electronics, healthcare, and pharmaceuticals. Despite their widespread adoption, concerns persist regarding potential adverse effects, necessitating vigilant risk management. This systematic literature review advocates for leveraging artificial intelligence (AI) and machine learning (ML) methodologies to enhance simulations and refine safety assessments for nanomaterials (NMs). Through a comprehensive examination of the existing literature, this study seeks to explain the pivotal role of AI in boosting NMs sustainability efforts across six key research themes. It explores their significance in advancing sustainability, hazard identification, and their diverse applications in this field. In addition, it evaluates the past sustainability strategies for NMs while proposing innovative avenues for future exploration. By conducting this comprehensive analysis, the research aims to illuminate the current landscape, identify challenges, and outline potential pathways for integrating AI and ML to promote sustainable practices within nanotechnology. Furthermore, it advocates for extending these technologies to monitor the real-world behaviour of NMs delivery. Through its thorough investigation, this systematic literature review endeavours to address current obstacles and pave the way for the safe and sustainable utilization of nanotechnology, thereby minimizing associated risks.