Probing AndroVul dataset for studies on Android malware classification

Namrud, Zakeya; Kpodjedo, Sègla; Talhi, Chamseddine; Alvine, Boaye Belle

doi:10.1016/j.jksuci.2021.08.033

Cited by 7 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fig. [13] shows the recall rate for the Naive Bayes algorithm is 92.00%, whereas the recall rate for the KNN algorithm is 88.00%.while the recall rate for the Logistic Regression algorithm is 89.00%. With a strong recall rate of 97.00%, though the proposed XGboost algorithm surpass the competitors.…”

Section: Resultsmentioning

confidence: 98%

“…The study in [13] comprised DTestBeign, a benign test suite that includes both malware and benign software intended for training. The AE-1 network was trained using the DTrain training dataset, the DTestMalware malware testing dataset, and the DTsafe safe data training dataset.…”

Section: Related Workmentioning

confidence: 99%

“…A Linear regression models Uses Permissions, API calls. 94.7% [10] Deep learning-based strategy Uses Encoded attributes 99.4% [11] Hybrid evolutionary strategy Uses GA and AIS model 98.6% [12] Using photos of app displays Uses texture, colour, and form 98.4% [13] Neural network-based classifier Uses noise as the input data 98.2%, All articles describe successful approaches for identifying Android malware that employ a variety of techniques such as linear regression models, autoencoders, evolutionary algorithms, image analysis, and adversarial defence mechanisms. Each approach produces excellent levels of accuracy ranging from 94.71% to 99.4%.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

A Hybrid Approach Based On Boosting Algorithm For Effective Android Malware Detection

Y. Sathwara,

Singh Mann

2024

IJCDS

View full text Add to dashboard Cite

Mobile phones are being used much more often and play a crucial role in everyday lives. These gadgets hold a tonne of personal information and provide a variety of functions and services. Mobile devices have become indispensable for those who utilise technology and communication since they are practical and effective. However, mobile systems are vulnerable to virus assaults just like any other type of information system. The development of hardware technologies has increased the complexity and performance of mobile apps. Additionally, the danger of security breaches and data theft rises with continued usage of mobile devices. Malicious actors may use mobile system flaws to obtain sensitive data, such as login passwords, financial information, and personal information. Mobile device makers and app developers are constantly changing their software to enhance security and performance in order to solve these issues. For instance, to safeguard user data, many mobile operating systems now have built-in security measures like firewalls, encryption, and two-factor authentication. In this paper, we present a linear regression model for detecting malware on the Android platform. This technique can assist in the prompt identification and obstruction of Android malware assaults, as well as improve app security by flagging any unnecessary permissions. Additionally, developers can use this approach to enhance the security of their apps and protect user data from unauthorized access.

show abstract

Section: Resultsmentioning

confidence: 98%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Hybrid Approach Based On Boosting Algorithm For Effective Android Malware Detection

Y. Sathwara,

Singh Mann

2024

IJCDS

View full text Add to dashboard Cite

show abstract

“…The widespread use of Android-powered devices in our daily lives has increased malicious applications, posing a threat to users' security and privacy [Aboaoja et al, 2022, Miranda et al, 2022. In the pursuit of mitigating this danger, researchers have proposed various approaches to detect malware on Android devices, where many of them are based on machine learning (ML) techniques [Zakeya et al, 2022, Ullah et al, 2022, Talbi et al, 2022, Alani and Awad, 2022, Scalas et al, 2021.…”

Section: Introductionmentioning

confidence: 99%

Explaining the Effectiveness of Machine Learning in Malware Detection: Insights from Explainable AI

Bragança,

Rocha,

Souto

et al. 2023

Anais Do XXIII Simpósio Brasileiro De Segurança Da Informação E De Sistemas Computacionais (SBSeg 2023)

View full text Add to dashboard Cite

We use Explainable Artificial Intelligence (XAI) to understand and assess the decisions made by ML models in Android malware detection. To evaluate malware detection, we conducted experiments using seven datasets. Our findings indicate that it is possible to accurately identify malware across multiple datasets. However, each dataset may have a different collection of features available. We also discuss the implications of incorporating expert-dependent features into the malware detection procedure. Such features have the potential to increase model accuracy by detecting minor indicators of harmful behaviour that automated algorithms may miss. However, because of the necessity for in-depth manual analysis, this strategy increases the resource and time requirements. It also risks adding human bias into the models and raises scaling issues in the continuously developing Android application landscape. Our results suggest that XAI techniques should be used to help malware analysis researchers understand how ML models work, rather than only concentrating on increasing accuracy.

show abstract

“…The rapid surge in digital service adoption due to the COVID-19 pandemic has left users vulnerable to an increasing number of malware attacks, resulting in data loss, information theft, and various cybercrimes [Aboaoja et al, 2022, Miranda et al, 2022. To address the new challenges of this scenario, the role of machine learning (ML) models in malware detection has gained significant traction (e.g., with new advanced research) [Zakeya et al, 2022].…”

Section: Introductionmentioning

confidence: 99%

Capturing the Behavior of Android Malware with MH-100K: A Novel and Multidimensional Dataset

Bragança,

Rocha,

Barcellos

et al. 2023

Anais Do XXIII Simpósio Brasileiro De Segurança Da Informação E De Sistemas Computacionais (SBSeg 2023)

View full text Add to dashboard Cite

The fast pace proliferation of Android malware continues to pose challenges to cybersecurity research. To help reshape the future of malware research, we introduce the MH-100K, a dataset that provides a holistic view through 101,975 APK samples, thousands of diverse features and metadata. We use the VirusTotal API to ensure accurate threat evaluation, combining multiple detection methods for precision. Our findings suggest MH-100K is a valuable resource for providing new insights about the malware landscape’s evolution.

show abstract

Probing AndroVul dataset for studies on Android malware classification

Cited by 7 publications

References 12 publications

A Hybrid Approach Based On Boosting Algorithm For Effective Android Malware Detection

A Hybrid Approach Based On Boosting Algorithm For Effective Android Malware Detection

Explaining the Effectiveness of Machine Learning in Malware Detection: Insights from Explainable AI

Capturing the Behavior of Android Malware with MH-100K: A Novel and Multidimensional Dataset

Contact Info

Product

Resources

About