IoT-DeepSense: Behavioral Security Detection of IoT Devices Based on Firmware Virtualization and Deep Learning

Wang, Jin; Liu, Chang; Xu, Jiangpei; Wang, Juan; Hao, Shirong; Yi, Wenzhe; Jing, Zhong

doi:10.1155/2022/1443978

Cited by 3 publications

(1 citation statement)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In response to the increasing severity of security issues in IoT devices [19], traditional security software and networkbased traffic detection are limited in their effectiveness. To address this urgent problem, we propose IoT-DeepSense, a behavioral security detection system for IoT devices.…”

Section: Related Workmentioning

confidence: 99%

SecureIoT: Novel Machine Learning Algorithms for Detecting and Preventing Attacks on IoT Devices

Srikanth Reddy Vutukuru

2024

jes

View full text Add to dashboard Cite

This research paper deals with the enhancement of Internet of Things (IoT) security through federated ensemble learning (FEI) and adversarial machine learning (AMLI) algorithms. The proposed approach strives to enhance the security of IoT devices and networks against numerous cyber threats. To address the increasing threat of IoT, the study will utilize advanced machine learning techniques in order to build more resilient defenses for IoT networks. Using the IoT-23_Combined dataset, the study scrutinized an array of IoT attack types, revealing the distribution and frequency of different attack categories. The FEI and AMLI models were trained and tested to detect and mitigate these IoT attacks, with the evaluation metrics being accuracy, precision, recall, and F1 score. The FEI model surpassed the AMLI model, registering superior performance in all metrics, with an accuracy of 87.94% and an F1 score of 88.44%. Concurrently, the study recommends the adoption of system hardening strategies and real-time response measures, including robust authentication methods, secure firmware updates, and security awareness training programs. The assessment of these measures was based on their implementation complexity, potential impact on system performance, and adaptability to changing threats. Conclusively, the research findings illustrate the potential of machine learning to bolster IoT security, suggesting a path towards more proactive defense mechanisms and the creation of a resilient IoT ecosystem. This study holds relevance for entities seeking to fortify their IoT security systems against an evolving threat landscape.

show abstract

Section: Related Workmentioning

confidence: 99%

SecureIoT: Novel Machine Learning Algorithms for Detecting and Preventing Attacks on IoT Devices

Srikanth Reddy Vutukuru

2024

jes

View full text Add to dashboard Cite

show abstract

Comparative Analysis of Firmware Security: A Proactive Paradigm for Enhancing Efficiency and Adaptability through Anomaly Detection

Ramesh

et al. 2023

2023 6th International Conference on Recent Trends in Advance Computing (ICRTAC)

View full text Add to dashboard Cite

Forex market directional trends forecasting with Bidirectional-LSTM and enhanced DeepSense network using all member-based optimizer

Dash,

Sahu,

Mishra

2023

IDT

View full text Add to dashboard Cite

This study focuses on successful Forex trading by emphasizing the importance of identifying market trends and utilizing trend analysis for informed decision-making. The authors collected low-correlated currency pair datasets to mitigate multicollinearity risk. Authors developed a two-stage predictive model that combines regression and classification tasks, using the predicted closing price to determine entry and exit points. The model incorporates Bi-directional long short-term memory (Bi-LSTM) for improved price forecasting and higher highs and lower lows (HHs-HLs and LHs-LLs) to identify trend changes. They proposed an enhanced DeepSense network (DSN) with all member-based optimization (AMBO-DSN) to optimize decision variables of DSN. The performance of the models was compared to various machine learning, deep learning, and statistical approaches including support vector regressor (SVR), artificial neural network (ANN), auto-regressive integrated moving average (ARIMA), vanilla-LSTM (V-LSTM), and recurrent neural network (RNN). The optimized form of DSN using genetic algorithm (GA), particle swarm optimization (PSO), and differential evolution (DE) was compared with AMBO-DSN, yielding satisfactory results that demonstrated comparable quality to the observed trends on the original currency pairs. The effectiveness and reliability of the AMBO-DSN approach in forecasting trends for USD/EUR, AUD/JPY, and CHF/INR currency pairs were validated through statistical analysis while considering computational cost.

show abstract

IoT-DeepSense: Behavioral Security Detection of IoT Devices Based on Firmware Virtualization and Deep Learning

Cited by 3 publications

References 30 publications

SecureIoT: Novel Machine Learning Algorithms for Detecting and Preventing Attacks on IoT Devices

SecureIoT: Novel Machine Learning Algorithms for Detecting and Preventing Attacks on IoT Devices

Comparative Analysis of Firmware Security: A Proactive Paradigm for Enhancing Efficiency and Adaptability through Anomaly Detection

Forex market directional trends forecasting with Bidirectional-LSTM and enhanced DeepSense network using all member-based optimizer

Contact Info

Product

Resources

About