3 research outputs found
An Efficient Deepfake Detection System using ConvoReinAutoNet and GeoFisherNet
No full textThis research proposes an efficient deepfake detection system using a hybrid optimization model and a new deep learning approach. This system is divided into two phases: (i) the training Phase and (ii) the detection Phase. The decision phase is the ultimate decision maker, wherein a new deep learning approach referred to as ConvoReinAutoNet(CRAN) is introduced by levering the layers of Convolutional Neural Networks (CNN), Deep Reinforcement Learning (DRL), and Autoencoders, respectively. The training phase is enriched with new feature fusion and a hybrid optimization-based optimal feature selection approach. The extracted temporal and texture features (newly introduced Improved Local Ternary Patterns (I-LTP)) from the pre-processed images of the deepfake database are fused using the new GeoFisherNet. The newest hybrid optimization method called Marine Predator Customized White Shark Optimizer (MCWO) is used to select the best features among the combined features, which represents the combination of both the Marine Predator Algorithm (MPA) and White Shark Optimization Algorithm (WSO). The suggested model has been implemented in python and validated in terms of detection efficiency over the existing approaches
An Efficient Deepfake Detection System Using ConvoReinAutoNet and GeoFisherNet
No full textThis research proposes an efficient deepfake detection system using a hybrid optimization model and a new deep learning approach. This system is divided into two phases: (i) the training Phase and (ii) the detection Phase. The decision phase is the ultimate decision maker, wherein a new deep learning approach referred to as ConvoReinAutoNet(CRAN) is introduced by levering the layers of Convolutional Neural Networks (CNN), Deep Reinforcement Learning (DRL), and Autoencoders, respectively. The training phase is enriched with new feature fusion and a hybrid optimization-based optimal feature selection approach. The extracted temporal and texture features (newly introduced Improved Local Ternary Patterns (I-LTP)) from the pre-processed images of the deepfake database are fused using the new GeoFisherNet. The newest hybrid optimization method called Marine Predator Customized White Shark Optimizer (MCWO) is used to select the best features among the combined features, which represents the combination of both the Marine Predator Algorithm (MPA) and White Shark Optimization Algorithm (WSO). The suggested model has been implemented in python and validated in terms of detection efficiency over the existing approaches
Formalizing Permission to Delegate and Delegation with Policy Interaction
No full textIn the context of Internet of Things (IoT) intelligent systems, the latest research regarding delegation using an access control model has gained attention, reflecting the need for models to support more functionalities in relation to hierarchical delegation. With respect to delegation procedures within access control, issues arise after delegation concerning the permissions to others with respect to revocation. Redundancy and conflict arising from delegation can occur depending on the delegation policies used within the hierarchical structure. This article discusses implementation of positive delegation represented by “YES” and negative delegation represented by “NO”. Furthermore, we also consider permission to delegate positively and negatively represented by (YES and NO). These challenges are addressed by creating additional features in a hierarchical policy model (HPol). The implementation was created using Python (ver. 3.10) code to verify the advantages of the approach, through experimentation under different scenarios. The model also has the capability to manage and adapt features of the Internet of Things (IoT) to a blockchain architecture, enhancing security and verification during the delegation process and increasing the scalability of Internet of Things (IoT) intelligent environment systems
