Control of Prey Disease in  Stage Structure Model

Wuhaib, S. A.; Abd, N. F.

doi:10.25130/j.v25i2.968

Cited by 6 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Vanishing and exploding gradients and, most importantly, the lack of As computing systems have improved, new kinds of DL architectures have been introduced, and improvements have been made in optimizers, activation functions, loss functions, and the disappearing and exploding gradient issues. DL is now being used to solve a variety of cyber security problems, and it outperforms that classical ML in every case depicts two types of DL architecture: generative and discriminative [19]. Deep Boltzmann machine (DBM), deep autoencoder (DAE), deep belief network (DBN), and recurrent structures are used to generate new ideas.…”

Section: Introductionmentioning

confidence: 99%

Federated Deep Learning Approaches for the Privacy and Security of IoT Systems

Alazzam

Alassery

Almulihi

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Using federated learning, which is a distributed machine learning approach, a machine learning model can train on a distributed data set without having to transfer any data between computers. Instead of using a centralised server for training, the model uses data stored locally on the device itself. After that, the server uses this model to create a jointly trained model. Federated learning asserts that privacy is preserved because no data is sent. Botnet attacks are detected using on-device decentralised traffic statistics and a deep autoencoder. This proposed federated learning approach addresses privacy and security concerns about data privacy and security rather than allowing data to be transferred or relocated off the network edge. In order to get the intended results of a previously centralised machine learning technique while also increasing data security, computation will be shifted to the edge layer. Up to 98% accuracy is achieved in anomaly detection with our proposed model using features like MAC IP and source/destination/IP for training. Our solution outperforms a standard centrally managed system in terms of attack detection accuracy, according to our comparative performance analysis.

show abstract

Section: Introductionmentioning

confidence: 99%

Federated Deep Learning Approaches for the Privacy and Security of IoT Systems

Alazzam

Alassery

Almulihi

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…New DL architectures have emerged, as have advancements in optimizers, activation functions, loss functions, and the vanishing and ballooning gradient 2 Applied Bionics and Biomechanics concerns. There are two kinds of DL architecture: generative and discriminative [18]. Ideas are generated using deep Boltzmann machines, deep autoencoders, deep belief networks, and recurrent structures.…”

Section: Introductionmentioning

confidence: 99%

Approaches to Federated Computing for the Protection of Patient Privacy and Security Using Medical Applications

Ahmed

Omer

Alshawwa

et al. 2022

Applied Bionics and Biomechanics

View full text Add to dashboard Cite

Computing model may train on a distributed dataset using Medical Applications, which is a distributed computing technique. Instead of a centralised server, the model trains on device data. The server then utilizes this model to train a joint model. The aim of this study is that Medical Applications claims no data is transferred, thereby protecting privacy. Botnet assaults are identified through deep autoencoding and decentralised traffic analytics. Rather than enabling data to be transmitted or relocated off the network edge, the problem of the study is in privacy and security in Medical Applications strategies. Computation will be moved to the edge layer to achieve previously centralised outcomes while boosting data security. Study Results in our suggested model detects anomalies with up to 98 percent accuracy utilizing MAC IP and source/destination/IP for training. Our method beats a traditional centrally controlled system in terms of attack detection accuracy.

show abstract

“…Advancements in computing systems have facilitated notable progress in various aspects of deep learning (DL), including designs, optimizers, activation functions, loss functions, and addressing challenges like vanishing and exploding gradients. DL has found extensive applications in addressing diverse cybersecurity challenges, consistently outperforming traditional machine learning methods [59]. DL architectures can be broadly categorized into generative and discriminative models.…”

Section: Deep Learningmentioning

confidence: 99%

FEDDBN-IDS: Federated Deep Belief Network-based Wireless Network Intrusion Detection System

et al. 2023

Preprint

View full text Add to dashboard Cite

Past two decades, Wi-Fi innovation has developed so generally that most contemporary gadgets are compact and use Wi-Fi to access the web. Because no physical boundary separates a wireless network from a wired network, Wi-Fi network security is seriously questioned, and current security measures are helpless to an extensive variety of attacks. The objective of this research was to evaluate a novel approach called federated learning as a potential solution to address privacy concerns and high costs associated with data collection in the field of recognizing network attacks. The study introduces FEDDBN-IDS, a ground-breaking intrusion detection system (IDS) that utilizes deep belief networks (DBNs) within a federated deep learning (FDL) framework to detect and identify cyber threats specifically in Wi-Fi networks. A DBN with stacked restricted Boltzmann machines (RBM) was trained on each device to learn the low-dimensional features from unlabelled private and local data. A central server later combines these models into a global model (FL) using federated learning. Subsequently, the central server adds fully connected SoftMax layers to the overall model to create a supervised neural network and train the model using freely available labeled AWID datasets. The results obtained from our experiments on the AWID intrusion detection dataset indicate that our federated strategy achieves a high level of classification accuracy, ranging from 88% to 98%.

show abstract

Control of Prey Disease in Stage Structure Model

Cited by 6 publications

References 5 publications

Federated Deep Learning Approaches for the Privacy and Security of IoT Systems

Federated Deep Learning Approaches for the Privacy and Security of IoT Systems

Approaches to Federated Computing for the Protection of Patient Privacy and Security Using Medical Applications

FEDDBN-IDS: Federated Deep Belief Network-based Wireless Network Intrusion Detection System

Contact Info

Product

Resources

About