“…Furthermore, the authors of [18] did not account for the model training time, which is the major drawback of LSTM and GRU. Work [19] proposed a cyberattacks detection mechanism using the combination of Variational Autoencoder (VAE) and LSTM. Although the detection performance is considerably high, the model in [19] faces difficulty in terms of running time since the LSTM block requires a long training time.…”
Section: Related Workmentioning
confidence: 99%
“…Work [19] proposed a cyberattacks detection mechanism using the combination of Variational Autoencoder (VAE) and LSTM. Although the detection performance is considerably high, the model in [19] faces difficulty in terms of running time since the LSTM block requires a long training time. Liu et al [20] presented an attention CNN-LSTM model within a FL framework for anomaly detection in IIoT edge devices.…”
Section: Related Workmentioning
confidence: 99%
“…However, ATRAF in both modes is proven to detect anomalies efficiently. In this experiment, the detection performance of FATRAF is compared with a recent detection work for ICS that applies Federated Learning [19] -Federated Learning called FL-VAE-LSTM. As Table 4 shows, FATRAF improves the detection performance in all metrics: Precision, Recall, F1score with both of the ICS data sets: Power Demand and Gas Pipeline.…”
Section: Experiments 1 -Federated Learning Vs Centralized Learningmentioning
“…Furthermore, the authors of [18] did not account for the model training time, which is the major drawback of LSTM and GRU. Work [19] proposed a cyberattacks detection mechanism using the combination of Variational Autoencoder (VAE) and LSTM. Although the detection performance is considerably high, the model in [19] faces difficulty in terms of running time since the LSTM block requires a long training time.…”
Section: Related Workmentioning
confidence: 99%
“…Work [19] proposed a cyberattacks detection mechanism using the combination of Variational Autoencoder (VAE) and LSTM. Although the detection performance is considerably high, the model in [19] faces difficulty in terms of running time since the LSTM block requires a long training time. Liu et al [20] presented an attention CNN-LSTM model within a FL framework for anomaly detection in IIoT edge devices.…”
Section: Related Workmentioning
confidence: 99%
“…However, ATRAF in both modes is proven to detect anomalies efficiently. In this experiment, the detection performance of FATRAF is compared with a recent detection work for ICS that applies Federated Learning [19] -Federated Learning called FL-VAE-LSTM. As Table 4 shows, FATRAF improves the detection performance in all metrics: Precision, Recall, F1score with both of the ICS data sets: Power Demand and Gas Pipeline.…”
Section: Experiments 1 -Federated Learning Vs Centralized Learningmentioning
“…[91], [92], [93], [94] [95], [96], [97], [98] [99], [100], [101], [102], [103] [104], [105], [106], [107], [108] Fig. 2: Existing Deep Learning Federated Intrusion Detection Systems by model architecture.…”
Section: Mlp Ae Vanillamentioning
confidence: 99%
“…Huong et al [92] proposed a cyberattack anomaly detection system for Industrial Internet of Things (IIoT) systems. In order to detect anomalies in time series data, they use a model architecture composed of an VAE-Encoder, an LSTM unit and an VAE-Decoder.…”
Disastrous site identification through the internet of UAVs is a current research area that aims to improve data sharing by connecting servers to the internet. Internet-connected unmanned aerial vehicles (UAVs) for aerial image classification necessitated the sharing of large datasets between the number of connected flying machines. The artificial intelligence model training to predict images need to compromise data privacy, consume a lot of energy, and high requirement of data communication. This article aims to propose and implement federated deep learning trained aerial image classification for disastrous sites through the internet of UAVs. The proposed model provides privacy-preserving and resource efficient deep learning by sharing only models rather than large datasets of images. Multisystem client-server federated learning UAV architecture was implemented and comparatively analyzed on basis of parameters namely, training-testing accuracy, train-testing loss, RAM-CPU utilization.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.