A Comparison of Machine and Deep Learning Models for Detection and Classification of Android Malware Traffic

Bovenzi, Giampaolo; Cerasuolo, Francesco; Montieri, Antonio; Nascita, Alfredo; Persico, Valerio; Pescapè, Antonio

doi:10.1109/iscc55528.2022.9912986

Cited by 12 publications

(3 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…II-C). (DNNs) [12,13], different types of AutoEncoders (AEs) [1,[33][34][35][36], one-and two-dimensional Convolutional Neural Networks (1D-and 2D-CNNs) [1,11,14,26,29,30,32,35,[37][38][39][40][41][42][43], variants of Recurrent Neural Networks (RNNs) such as Long Short-Term Memory (LSTM) [1,29,34,39,44,45] and Gated Recurrent Unit (GRU) [11,30,38,45,46], possibly exploiting the composition capabilities of hybrid DL architectures [1,30,44]. The way input data are fed to such architectures is paramount for taking full advantage of the DL paradigm.…”

Section: Background and Related Workmentioning

confidence: 99%

Improving Performance, Reliability, and Feasibility in Multimodal Multitask Traffic Classification with XAI

Nascita

Montieri

Aceto

et al. 2023

IEEE Trans. Netw. Serv. Manage.

View full text Add to dashboard Cite

The promise of Deep Learning (DL) in solving hard problems such as network Traffic Classification (TC) is being held back by the severe lack of transparency and explainability of this kind of approaches. To cope with this strongly felt issue, the field of eXplainable Artificial Intelligence (XAI) has been recently founded, and is providing effective techniques and approaches. Accordingly, in this work we investigate interpretability via XAIbased techniques to understand and improve the behavior of state-of-the-art multimodal and multitask DL traffic classifiers. Using a publicly available security-related dataset (ISCX VPN-NONVPN), we explore and exploit XAI techniques to characterize the considered classifiers providing global interpretations (rather than sample-based ones), and define a novel classifier, DISTILLER-EVOLVED, optimized along three objectives: performance, reliability, feasibility. The proposed methodology proves as highly appealing, allowing to much simplify the architecture to get faster training time and shorter classification time, as fewer packets must be collected. This is at the expenses of negligible (or even positive) impact on classification performance, while understanding and controlling the interplay between inputs, model complexity, performance, and reliability.

show abstract

Section: Background and Related Workmentioning

confidence: 99%

Improving Performance, Reliability, and Feasibility in Multimodal Multitask Traffic Classification with XAI

Nascita

Montieri

Aceto

et al. 2023

IEEE Trans. Netw. Serv. Manage.

View full text Add to dashboard Cite

show abstract

“…A comparison of traditional ML and DL models for the detection and classification of Android malware traffic is presented by Bovenzi et al (2022). The paper suggests that DL-based techniques can improve the effectiveness of Android malware detection and classification.…”

Section: Introductionmentioning

confidence: 99%

Securing Mobile Devices from Malware: A Faceoff Between Federated Learning and Deep Learning Models for Android Malware Classification

Subramanian,

Ravi,

Shaan

et al. 2024

Journal of Computer Science

View full text Add to dashboard Cite

Amidst the escalating threats of android malware, urgency mounts to detect issues while safeguarding user privacy. Traditional machine learning and deep learning methods, dealt with scalability challenges and privacy compromises, finding a potential remedy in federated learning. This study introduces a groundbreaking federated learning-based methodology and compares federated learning with traditional deep learning techniques for Android malware classification, employing renowned datasets, including Drebin, Malgenome, Tuandromd, and Kronodroid. Shifting gears, a federated learning-based approach for malware classification excels in accuracy, scalability, and privacy preservation. Acknowledging limitations and ethical considerations, the study underscores the need for robust privacy measures and dataset transparency. This study unveils federated learning's prowess in android malware classification, opening doors to privacy-driven applications in diverse domains.

show abstract

“…Over 1.5 million IoT devices were affected, and the malware targeted numerous famous internet services such as Gmail, Amazon, and others. A cybersecurity developer team in Moscow acquired 121,600 IoT malware samples in 2019, roughly triple the 35,618 samples it acquired in 2018, and over 130,000 variant IoT malware samples whose attacking tactics were smartly evolved were recommended security on these devices [ 5 ].…”

Section: Introductionmentioning

confidence: 99%

Detection of Android Malware in the Internet of Things through the K-Nearest Neighbor Algorithm

Babbar,

Rani,

Sah

et al. 2023

Sensors

View full text Add to dashboard Cite

Predicting attacks in Android malware devices using machine learning for recommender systems-based IoT can be a challenging task. However, it is possible to use various machine-learning techniques to achieve this goal. An internet-based framework is used to predict and recommend Android malware on IoT devices. As the prevalence of Android devices grows, the malware creates new viruses on a regular basis, posing a threat to the central system’s security and the privacy of the users. The suggested system uses static analysis to predict the malware in Android apps used by consumer devices. The training of the presented system is used to predict and recommend malicious devices to block them from transmitting the data to the cloud server. By taking into account various machine-learning methods, feature selection is performed and the K-Nearest Neighbor (KNN) machine-learning model is proposed. Testing was carried out on more than 10,000 Android applications to check malicious nodes and recommend that the cloud server block them. The developed model contemplated all four machine-learning algorithms in parallel, i.e., naive Bayes, decision tree, support vector machine, and the K-Nearest Neighbor approach and static analysis as a feature subset selection algorithm, and it achieved the highest prediction rate of 93% to predict the malware in real-world applications of consumer devices to minimize the utilization of energy. The experimental results show that KNN achieves 93%, 95%, 90%, and 92% accuracy, precision, recall and f1 measures, respectively.

show abstract

A Comparison of Machine and Deep Learning Models for Detection and Classification of Android Malware Traffic

Cited by 12 publications

References 27 publications

Improving Performance, Reliability, and Feasibility in Multimodal Multitask Traffic Classification with XAI

Improving Performance, Reliability, and Feasibility in Multimodal Multitask Traffic Classification with XAI

Securing Mobile Devices from Malware: A Faceoff Between Federated Learning and Deep Learning Models for Android Malware Classification

Detection of Android Malware in the Internet of Things through the K-Nearest Neighbor Algorithm

Contact Info

Product

Resources

About