DNNdroid: Android Malware Detection Framework Based on Federated Learning and Edge Computing

Mahindru, Arvind; Arora, Himani

doi:10.1007/978-3-031-23095-0_7

Cited by 7 publications

(3 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, researchers have started to employ FL ( federated learning) technology to achieve privacy protection and high accuracy in Android malware detection and classification. In [19], the authors use federated learning, combining data from multiple users, to improve malware detection and ensure privacy preservation. The authors in [20] propose another framework based on a combination of semi-supervised machine learning and federated learning.…”

Section: Related Workmentioning

confidence: 99%

Enhancing Robustness within the Collaborative Federated Learning Framework: A Novel Grouping Algorithm for Edge Clients

Su,

Liu,

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

In this study, we introduce a novel collaborative federated learning (FL) framework, aiming at enhancing robustness in distributed learning environments, particularly pertinent to IoT and industrial automation scenarios. At the core of our contribution is the development of an innovative grouping algorithm for edge clients. This algorithm employs a distinctive ID distribution function, enabling efficient and secure grouping of both normal and potentially malicious clients. Our proposed grouping scheme accurately determines the numerical difference between normal and malicious groups under various network scenarios. Our method addresses the challenge of model poisoning attacks, ensuring the accuracy of outcomes in a collaborative federated learning framework. Our numerical experiments demonstrate that our grouping scheme effectively limits the number of malicious groups. Additionally, our collaborative FL framework has shown resilience against various levels of poisoning attack abilities and maintained high prediction accuracy across a range of scenarios, showcasing its robustness against poisoning attacks.

show abstract

Section: Related Workmentioning

confidence: 99%

Enhancing Robustness within the Collaborative Federated Learning Framework: A Novel Grouping Algorithm for Edge Clients

Su,

Liu,

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…A typical HIDS would conduct its activities at the host level to tackle this problem. There, it would monitor and analyze all traffic events that are going to take place on the program's application files, responses, and OS version [17]. In the transportation industry, traffic operations of this kind are often known as audit trials.…”

Section: • Host-based Intrusion Detection Systems (Hids)mentioning

confidence: 99%

Enhancing Intrusion Detection Systems With a Novel Hybrid Learning-Based Framework

2023

ecb

View full text Add to dashboard Cite

The proliferation of cyber threats and the increasing sophistication of attacks have necessitated the development of robust Intrusion Detection Systems (IDS) to protect sensitive information and network infrastructures. Traditional IDS methods often struggle to effectively detect and respond to emerging threats due to their reliance on static rule-based approaches. To address these limitations, this paper presents a simplified and novel hybrid learning-based framework for strengthening IDS. The proposed framework integrates the strengths of two prominent Machine Learning (ML) techniques: Deep Learning (DL) and Ensemble Learning. DL models, specifically Convolutional Neural Networks (CNNs), are employed to extract high-level features from network traffic data, enabling the system to automatically learn and adapt to complex attack patterns. Ensemble learning is then utilized to combine multiple classifiers, leveraging the diversity of their decision boundaries, and enhancing the overall detection performance. The experimental results demonstrate that the suggested framework achieves superior detection accuracy, outperforming traditional rule-based approaches as well as standalone DL and ensemble learning models.

show abstract

“…Mahindru and Arora present a federated learning approach to detecting malware in IoT networks (Mahindru and Arora, 2022). They used a CNN to learn from local data on IoT devices, federated averaging to aggregate model weights, and dynamic clustering to group similar devices for more efficient learning.…”

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

DNNdroid: Android Malware Detection Framework Based on Federated Learning and Edge Computing

Cited by 7 publications

References 29 publications

Enhancing Robustness within the Collaborative Federated Learning Framework: A Novel Grouping Algorithm for Edge Clients

Enhancing Robustness within the Collaborative Federated Learning Framework: A Novel Grouping Algorithm for Edge Clients

Enhancing Intrusion Detection Systems With a Novel Hybrid Learning-Based Framework

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

Contact Info

Product

Resources

About