Federated learning for malware detection in IoT devices

Rey, Valerian; Sánchez, Pedro Miguel Sánchez; Celdrán, Alberto Huertas; Bovet, Gérôme

doi:10.1016/j.comnet.2021.108693

Cited by 206 publications

(81 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, Dou et al ( 2021 ) applied FL on data from 132 patients from seven multinational medical centers from Hong Kong, Mainland China, and Germany to develop models for detecting COVID-19 lung abnormalities in Computerized Tomography (CT) scans. Rey et al ( 2022 ) developed FL framework for malware detection in IoT devices. The framework enables the training and testing of both supervised and unsupervised models.…”

Section: Related Workmentioning

confidence: 99%

Federated Learning for Privacy-Aware Human Mobility Modeling

Ezequiel

Gjoreski

Langheinrich

2022

Front. Artif. Intell.

View full text Add to dashboard Cite

Human mobility modeling is a complex yet essential subject of study related to modeling important spatiotemporal events, including traffic, disease spreading, and customized directions and recommendations. While spatiotemporal data can be collected easily via smartphones, current state-of-the-art deep learning methods require vast amounts of such privacy-sensitive data to generate useful models. This work investigates the creation of spatiotemporal models using a Federated Learning (FL) approach—a machine learning technique that avoids sharing personal data with centralized servers. More specifically, we examine three centralized models for next-place prediction: a simple Gated Recurrent Unit (GRU) model, as well as two state-of-the-art centralized approaches, Flashback and DeepMove. Flashback is a Recurrent Neural Network (RNN) that utilizes historical hidden states with similar context as the current spatiotemporal context to improve performance. DeepMove is an attentional RNN that aims to capture human mobility's regularity while coping with data sparsity. We then implemented models based on FL for the two best-performing centralized models. We compared the performance of all models using two large public datasets: Foursquare (9,450 million check-ins, February 2009 to October 2010) and Gowalla (3,300 million check-ins, April 2012 to January 2014). We first replicated the performance of both Flashback and DeepMove, as reported in the original studies, and compared them to the simple GRU model. Flashback and GRU proved to be the best performing centralized models, so we further explored both in FL scenarios, including several parameters such as the number of clients, rounds, and epochs. Our results indicated that the training process of the federated models was less stable, i.e., the FL versions of both Flashback and GRU tended to have higher variability in the loss curves. The higher variability led to a slower convergence and thus a poorer performance when compared to the corresponding centralized models. Model performance was also highly influenced by the number of federated clients and the sparsity of the evaluation dataset. We additionally provide insights into the technical challenges of applying FL to state-of-the-art deep learning methods for human mobility.

show abstract

Section: Related Workmentioning

confidence: 99%

Federated Learning for Privacy-Aware Human Mobility Modeling

Ezequiel

Gjoreski

Langheinrich

2022

Front. Artif. Intell.

View full text Add to dashboard Cite

show abstract

“…BCB and BAB are still being improvised to make them more dependable and scalable over various CPU architectures and forthcoming IoT devices. Valerian Rey 14 presented a paradigm based on a new technology known as Federated Learning (FL) to overcome this. The present scheme was conducted using the N-BaIoT dataset, which comprises network traffic across various IoT devices that have been tainted by malware.…”

Section: Related Workmentioning

confidence: 99%

An Efficient Framework for Detection and Classification of IoT Botnet Traffic

et al. 2022

View full text Add to dashboard Cite

The Internet of Things (IoT) has become an integral requirement to equip common life. According to IDC, the number of IoT devices may increase exponentially up to a trillion in near future. Thus, their cyberspace having inherent vulnerabilities leads to various possible serious cyber-attacks. So, the security of IoT systems becomes the prime concern for its consumers and businesses. Therefore, to enhance the reliability of IoT security systems, a better and real-time approach is required. For this purpose, the creation of a real-time dataset is essential for IoT traffic analysis. In this paper, the experimental testbed has been devised for the generation of a real-time dataset using the IoT botnet traffic in which each of the bots consists of several possible attacks. Besides, an extensive comparative study of the proposed dataset and existing datasets are done using popular Machine Learning (ML) techniques to show its relevance in the real-time scenario.

show abstract

“…Rey et al 22 evaluated the possibility afforded by FL for IoT malware detection and researched the security problems in this situation. A framework that used FL to identify malware impacting IoT devices was also provided.…”

Section: Organization Of Fl‐based Iotmentioning

confidence: 99%

Federated learning‐based IoT: A systematic literature review

Hosseinzadeh

Hemmati

Rahmani

2022

Int J Communication

View full text Add to dashboard Cite

Summary The Internet of Things (IoT) has a significant impact on our daily lives as applications, services, devices, and industries become more intelligent. Artificial intelligence (AI) is expected to significantly influence machine learning training on IoT devices without data sharing. Federated learning (FL) is a distributed machine learning method used in many IoT smart devices; however, FL ensures IoT security and privacy. The systematic literature review (SLR) method is used in this paper to review recently published articles in the FL‐based IoT domain. We analyzed 39 papers that were published between 2018 and March 2022. According to the evaluation factors, the accuracy factor has a high percentage in the FL‐based IoT domain by 29%, and the epoch has 23%, the time has 18%, the energy consumption has 9%, the delay has 9%, the communication overhead has 6%, and the privacy has 6%. Finally, we discuss future research challenges and open issues in the context of FL‐based IoT.

show abstract

Federated learning for malware detection in IoT devices

Cited by 206 publications

References 19 publications

Federated Learning for Privacy-Aware Human Mobility Modeling

Federated Learning for Privacy-Aware Human Mobility Modeling

An Efficient Framework for Detection and Classification of IoT Botnet Traffic

Federated learning‐based IoT: A systematic literature review

Contact Info

Product

Resources

About