A Multilayer Deep Learning Approach for Malware Classification in 5G-Enabled IIoT

Ahmed, Imran; Anisetti, Marco; Ahmad, Awais; Jeon, Gwanggil

doi:10.1109/tii.2022.3205366

Cited by 33 publications

(10 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As demonstrated in the above discussion, utilizing SPP 50 enables us to input varying sizes of training samples into CNN without compromising information. This approach allows using traditional platform‐based malware samples to train models for IoT malware variant detection 51 . By leveraging a larger sample set, we can significantly enhance detection accuracy and improve our ability to identify and mitigate emerging threats.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

MUDROID: Android malware detection and classification based on permission and behavior for autonomous vehicles

Tang,

Da,

Wang

et al. 2023

Trans Emerging Tel Tech

View full text Add to dashboard Cite

With the growing popularity of autonomous vehicles, ensuring their safety has become a significant concern. Vehicle manufacturers have incorporated the Android operating system to enhance user convenience. However, the Android operating system's diversity and vulnerability may significantly impact autonomous vehicles because these natures lead to a critical threat in autonomous vehicle security: Android malware. The complex nature of multi‐data sources fusion in autonomous driving systems has resulted in low detection efficiency and accuracy for Android malware. Given the security requirements for autonomous‐driving systems, this article presents an Android malware classification method centered around the multifeature fusion and deep learning architecture designed to detect and classify Android malware within autonomous‐driving systems. The proposed MUDROID framework relies on the Android permission mechanism and behavioral feature to formulate a malware classification model. Comprising four essential components—feature extraction, representation, multifeature fusion, and classifier training, MUDROID leverages the advantages of CNN and GCN combination model and is adept at extracting and interpreting multidimensional features, consequently constructing a multifeature fusion classifier to amplify the efficiency and accuracy of Android malware detection and classification. The experiment results support MUDROID's superior classification performance, with an impressive Android malware detection accuracy rate of 98.69% and family classification (95.42%). The proposed method can detect and classify Android malware effectively, thus elevating the security and robustness of the self‐driving system. Additionally, the approach in this article also addresses feature representation issues in detecting malware variants, facilitating the recognition of Android malware variants across diverse platforms.

show abstract

Section: Methodsmentioning

confidence: 99%

“…This approach allows using traditional platform-based malware samples to train models for IoT malware variant detection. 51 By leveraging a larger sample set, we can significantly enhance detection accuracy and improve our ability to identify and mitigate emerging threats.…”

Section: ) Convolutional Neural Network Modulementioning

confidence: 99%

MUDROID: Android malware detection and classification based on permission and behavior for autonomous vehicles

Tang,

Da,

Wang

et al. 2023

Trans Emerging Tel Tech

View full text Add to dashboard Cite

show abstract

“…Our proposed method outperforms the existing deep malware detection and image classification methods by a notable margin. In addition to that, we illustrate an optimization strategy for deploying our deep model in low-power edge devices to reveal the practicability of deep, efficient malware detection for securing future solutions, including securing IoT and 5G/6G infrastructures [35,36]. To the best concern, this is the first work in the literature demonstrating the optimization and practicability of malware detection on real-edge hardware with sophisticated experiments.…”

Section: Introductionmentioning

confidence: 99%

Securing Edge Devices: Malware Classification with Dual-Attention Deep Network

Alandjani

2024

Applied Sciences

View full text Add to dashboard Cite

Detecting malware is a crucial defense mechanism against potential cyber-attacks. However, current methods illustrate significant limitations in achieving high performance while maintaining faster inference on edge devices. This study proposes a novel deep network with dual-attention feature refinement on a two-branch deep network to learn real-time malware detection on edge platforms. The proposed method introduces lightweight spatial-asymmetric attention for refining the extracted features of its backbone and multi-head attention to correlate learned features from the network branches. The experimental results show that the proposed method can significantly outperform existing methods in quantitative evaluation. In addition, this study also illustrates the practicability of a lightweight deep network on edge devices by optimizing and deploying the model directly on the actual edge hardware. The proposed optimization strategy achieves a frame rate of over 545 per second on low-power edge devices.

show abstract

“…This is achieved by utilizing a client and a server [12]. Servers in the cloud can detect malicious software in files sent to them by clients in the cloud [13]. Recent studies have demonstrated that malware detection rates can be improved and that each malware sample can be thoroughly analyzed using cloudbased detection [14].…”

Section: Introductionmentioning

confidence: 99%

Advances in Malware Analysis and Detection in Cloud Computing Environments: A Review

Rao,

Jain

2024

IJSSE

View full text Add to dashboard Cite

Cloud computing, integral for data storage and online services, presents significant advantages over traditional data storage and distribution methods, including enhanced convenience, on-demand storage, scalability, and cost efficiency. Its growing adoption in securing Internet of Things (IoT) and cyber-physical systems (CPS) against various cyber threats offers numerous opportunities. Despite the continuous evolution of malware and the lack of a universally effective detection method, cloud environments provide a promising approach for malware detection. Cloud computing, recognized for its efficiency, scalability, flexibility, and reliability on elastic resources, is widely utilized in the IT industry to support IT infrastructure and services. However, one of the foremost security challenges faced is malware attacks. Certain antivirus scanners struggle to detect metamorphic or encrypted malware in cloud environments due to complexity and scale, allowing such threats to evade detection. High detection rates with precision in reducing false positives are essential. Machine learning (ML) classifiers, a vital component in Artificial Intelligence (AI) systems, require training on extensive data volumes to develop credible models with high detection rates. Traditional detection methods face challenges in identifying complex malware, as modern malware employs contemporary packaging and obfuscation techniques to circumvent security measures. This paper provides a detailed discussion on detecting malware in cloud environments and the advantages of cloud computing in safeguarding IoT and CPS from cyber attacks. It presents a survey on malware analysis and detection models, aiding researchers in identifying limitations of traditional malware detection models in cloud environments and inspiring the design of innovative models with enhanced quality of service levels.

show abstract

A Multilayer Deep Learning Approach for Malware Classification in 5G-Enabled IIoT

Cited by 33 publications

References 30 publications

MUDROID: Android malware detection and classification based on permission and behavior for autonomous vehicles

MUDROID: Android malware detection and classification based on permission and behavior for autonomous vehicles

Securing Edge Devices: Malware Classification with Dual-Attention Deep Network

Advances in Malware Analysis and Detection in Cloud Computing Environments: A Review

Contact Info

Product

Resources

About