The proliferation of the Internet of Things (IoT) has brought unprecedented connectivity, introducing complex trust and reputation management challenges across vast, heterogeneous networks. This paper introduces the DeepTrust framework, a novel approach leveraging deep learning algorithms to assess and manage trust and reputation in IoT environments dynamically. We demonstrate the framework’s superiority in accurately identifying trustworthy and untrustworthy devices through extensive experiments, significantly enhancing IoT security. DeepTrust has demonstrated marked superiority over existing methods, showcasing enhanced accuracy in identifying trustworthy versus untrustworthy devices, thereby significantly bolstering IoT network security. Specifically, our results reveal an improvement in accuracy by 15%, precision by 20%, and recall rates by 18% compared to conventional models, highlighting DeepTrust’s effectiveness in real-time, adaptive trust assessments. There are several avenues for enhancing and expanding the DeepTrust framework. Future research will explore optimization techniques for reducing computational demands, enabling deployment on resource-constrained IoT devices. Additionally, incorporating incremental learning mechanisms could improve the framework’s adaptability to new and changing IoT environments. Enhancing data privacy and security measures within the framework constitutes another critical development area, ensuring the protection of sensitive information used in trust assessments. Lastly, extending the framework’s applicability across various IoT domains and applications presents a promising direction, aiming to establish a universal trust management solution adaptable to the unique requirements of different IoT ecosystems. By outlining these potential future directions, we aim to highlight the current achievements of the DeepTrust framework and chart a course for its continued development and refinement. This comprehensive approach underscores our commitment to advancing the field of IoT trust and reputation management, paving the way for more secure and reliable IoT networks.

As the manufacturing industry advances towards Industry 5.0, which heavily integrates advanced technologies such as cyber-physical systems, artificial intelligence, and the Internet of Things (IoT), the potential for web-based attacks increases. Cybersecurity concerns remain a crucial challenge for Industry 5.0 environments, where cyber-attacks can cause devastating consequences, including production downtime, data breaches, and even physical harm. To address this challenge, this research proposes an innovative deep-learning methodology for detecting web-based attacks in Industry 5.0. Convolutional neural networks (CNNs), recurrent neural networks (RNNs), and transformer models are examples of deep learning techniques that are investigated in this study for their potential to effectively classify attacks and identify anomalous behavior. The proposed transformer-based system outperforms traditional machine learning methods and existing deep learning approaches in terms of accuracy, precision, and recall, demonstrating the effectiveness of deep learning for intrusion detection in Industry 5.0. The study’s findings showcased the superiority of the proposed transformer-based system, outperforming previous approaches in accuracy, precision, and recall. This highlights the significant contribution of deep learning in addressing cybersecurity challenges in Industry 5.0 environments. This study contributes to advancing cybersecurity in Industry 5.0, ensuring the protection of critical infrastructure and sensitive data.

Intrusion detection in Internet of Things (IoT)-based wireless sensor networks (WSNs) is essential due to their widespread use and inherent vulnerability to security breaches. Traditional centralized intrusion detection systems (IDS) face significant challenges in data privacy, computational efficiency, and scalability, particularly in resource-constrained IoT environments. This study aims to create and assess a federated learning (FL) framework that integrates with long short-term memory (LSTM) networks for efficient intrusion detection in IoT-based WSNs. We design the framework to enhance detection accuracy, minimize false positive rates (FPR), and ensure data privacy, while maintaining system scalability. Using an FL approach, multiple IoT nodes collaboratively train a global LSTM model without exchanging raw data, thereby addressing privacy concerns and improving detection capabilities. The proposed model was tested on three widely used datasets: WSN-DS, CIC-IDS-2017, and UNSW-NB15. The evaluation metrics for its performance included accuracy, F1 score, FPR, and root mean square error (RMSE). We evaluated the performance of the FL-based LSTM model against traditional centralized models, finding significant improvements in intrusion detection. The FL-based LSTM model achieved higher accuracy and a lower FPR across all datasets than centralized models. It effectively managed sequential data in WSNs, ensuring data privacy while maintaining competitive performance, particularly in complex attack scenarios. FL and LSTM networks work well together to make a strong way to find intrusions in IoT-based WSNs, which improves both privacy and detection. This study underscores the potential of FL-based systems to address key challenges in IoT security, including data privacy, scalability, and performance, making the proposed framework suitable for real-world IoT applications.

In the rapidly advancing domain of smart manufacturing, securing data integrity and preventing unauthorized access are critical challenges. This study introduces a novel approach that synergizes anomaly detection techniques with Zero-Knowledge Proofs (ZKPs) to fortify the security framework of smart manufacturing systems. Our methodology employs a combination of data preprocessing, including statistical imputation and data smoothing, alongside advanced anomaly detection using classification methods and neural networks, particularly focusing on deep learning architectures. The detected anomalies undergo verification through zk-SNARKs, a specialized ZKP scheme, ensuring a robust validation process without compromising data confidentiality. Our findings reveal a notable enhancement in the accuracy of anomaly detection, achieving detection rates of approximately 95% for temperature fluctuations and 90% for pressure irregularities, with a significant reduction in false positives. This performance is markedly superior to traditional methods and aligns closely with the highest efficacy rates reported in contemporary studies. Moreover, the utilization of ZKPs for anomaly verification demonstrated a 98% success rate, ensuring the secure and private verification of anomalies. The integration of anomaly detection with ZKPs presents a significant leap forward in addressing the security vulnerabilities inherent in smart manufacturing. This study not only showcases the effectiveness of our approach in enhancing data security and integrity but also sets a benchmark for future research in creating more resilient and trustworthy industrial operations.

Background: Cancer remains one of the leading causes of mortality globally, with conventional chemotherapy often resulting in severe side effects and limited effectiveness. Recent advancements in bioinformatics and machine learning, particularly deep learning, offer promising new avenues for cancer treatment through the prediction and identification of anticancer peptides. Objective: This study aimed to develop and evaluate a deep learning model utilizing a two-dimensional convolutional neural network (2D CNN) to enhance the prediction accuracy of anticancer peptides, addressing the complexities and limitations of current prediction methods. Methods: A diverse dataset of peptide sequences with annotated anticancer activity labels was compiled from various public databases and experimental studies. The sequences were preprocessed and encoded using one-hot encoding and additional physicochemical properties. The 2D CNN model was trained and optimized using this dataset, with performance evaluated through metrics such as accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC-ROC). Results: The proposed 2D CNN model achieved superior performance compared to existing methods, with an accuracy of 0.87, precision of 0.85, recall of 0.89, F1-score of 0.87, and an AUC-ROC value of 0.91. These results indicate the model’s effectiveness in accurately predicting anticancer peptides and capturing intricate spatial patterns within peptide sequences. Conclusion: The findings demonstrate the potential of deep learning, specifically 2D CNNs, in advancing the prediction of anticancer peptides. The proposed model significantly improves prediction accuracy, offering a valuable tool for identifying effective peptide candidates for cancer treatment. Future Work: Further research should focus on expanding the dataset, exploring alternative deep learning architectures, and validating the model’s predictions through experimental studies. Efforts should also aim at optimizing computational efficiency and translating these predictions into clinical applications.

Background: Accurate brain tumor detection is essential for effective treatment and improved patient outcomes, yet conventional MRI classification methods often struggle with complex and variable imaging data. This study introduces the Transformative Transfer Learning (TTL) model, leveraging pre-trained deep neural networks fine-tuned for MRI brain tumor classification, using datasets from Nickparvar and Cheng. High-quality inputs were achieved through preprocessing, including resizing, normalization, noise reduction, and data augmentation. The TTL model, employing architectures such as VGG16, ResNet-50, InceptionV3, and DenseNet-121, demonstrated a substantial improvement over traditional methods, achieving an accuracy of 94.5%, sensitivity of 92.8%, and specificity of 93.1%. Additionally, the model yielded a precision of 93.2%, recall of 92.8%, F1-score of 93.0%, and true positive and true negative rates of 92.8% and 93.1%, respectively. Training and validation loss values of 0.15 and 0.18 confirm effective model convergence. These metrics underscore the model’s potential as a robust tool in clinical diagnostics, providing a pathway to more accurate and efficient MRI-based brain tumor detection.