A Deep Learning Approach to Malware Detection: Leveraging Multilayer Perceptron for Permission-Based

Ameerah Muhsinah Jamil (1), Mohd Faizal Ab Razak (2), Sharfah Ratibah Tuan Mat (3), Mahir Pradana (4), Deden Witarsyah (5)
(1) Faculty of Computing, University Malaysia Pahang, Gambang, Kuantan, Pahang, Malaysia
(2) Faculty of Computing, University Malaysia Pahang, Gambang, Kuantan, Pahang, Malaysia
(3) Department of Mathematics and Computer Science, Politeknik Sultan Haji Ahmad Shah, Malaysia
(4) Department of Business Administration, Telkom University, Bandung, Indonesia
(5) Faculty of Computer Science and Information Technology, Universiti Tun Hussein Onn Malaysia, Malaysia
Fulltext View | Download
How to cite (IJASEIT) :
[1]
A. M. Jamil, M. F. Ab Razak, S. R. Tuan Mat, M. Pradana, and D. Witarsyah, “A Deep Learning Approach to Malware Detection: Leveraging Multilayer Perceptron for Permission-Based ”, Int. J. Adv. Sci. Eng. Inf. Technol., vol. 15, no. 3, pp. 960–967, Jun. 2025.
The active growth of social networking worldwide has encouraged the emergence of malware that threatens such devices. Continuously researching according to malware threats has been accomplished to prevent the malware spread. Yet, malware attack continues to change and occur in very large numbers that requiring better solutions. In this paper, we proposed a Multilayer perceptron, a type of deep learning approach to tackle malware attacks focused on permission features. The study conducted eight experiments with 15, 20, 25, and 30 selected features for both algorithms, utilizing a dataset of 10,000 applications—5,000 benign (Androzoo) and 5,000 malicious (Drebin). The detection process involved three phases: data gathering, preprocessing, and classification, employing 10-fold cross-validation. The validation through all the experiments performed in this study achieved the highest accuracy of 98.2% accuracy, though other feature sets exhibited minimal variation in performance. Further dataset analysis revealed that the INTERNET permission was prevalent in 99% of malware samples and 81% of benign applications, highlighting its widespread use. This study underscores the importance of feature selection in Android malware detection and suggests that future research integrate risk assessment to classify and prioritize permission requests. Risk-based analysis could enhance malware detection by systematically evaluating potential security threats, addressing the rapid proliferation of malware. The findings contribute to the ongoing development of robust Android security mechanisms and encourage further research in permission-based threat mitigation strategies.

N. S. Nordin and M. A. Ismail, "A hybridization of butterfly optimization algorithm and harmony search for fuzzy modelling in phishing attack detection," Neural Comput. Appl., vol. 35, no. 7, pp. 5501-5512, Mar. 2023, doi: 10.1007/s00521-022-07957-0.

M. F. A. Razak, N. B. Anuar, R. Salleh, and A. Firdaus, "The rise of 'malware': Bibliometric analysis of malware study," J. Netw. Comput. Appl., vol. 75, pp. 58-76, 2016, doi: 10.1016/j.jnca.2016.08.022.

C. Yuan et al., "Android applications categorization using Bayesian classification," in Proc. Int. Conf. Cyber-Enabled Distrib. Comput. Knowl. Discov. (CyberC), 2016, pp. 173-176, doi:10.1109/CyberC.2016.42.

Z. U. Rehman et al., "Machine learning-assisted signature and heuristic-based detection of malwares in Android devices," Comput. Electr. Eng., vol. 69, pp. 828-841, Jul. 2018, doi:10.1016/j.compeleceng.2017.11.028.

O. Koucham, T. Rachidi, and N. Assem, "Host intrusion detection using system call argument-based clustering combined with Bayesian classification," in Proc. SAI Intell. Syst. Conf. (IntelliSys), 2015, pp. 1010-1016, doi: 10.1109/IntelliSys.2015.7361267.

C. H. Liu, Z. J. Zhang, and S. D. Wang, "An android malware detection approach using Bayesian inference," in Proc. IEEE Int. Conf. Comput. Inf. Technol. (CIT), 2016, pp. 476-483, doi: 10.1109/CIT.2016.76.

N. N. M. Nasri et al., "Android malware detection system using machine learning," Int. J. Adv. Trends Comput. Sci. Eng., vol. 9, no. 1.5, pp. 327-333, 2020, doi: 10.30534/ijatcse/2020/4691.52020.

O. Yildiz and I. A. Doǧru, "Permission-based Android malware detection system using feature selection with genetic algorithm," Int. J. Softw. Eng. Knowl. Eng., vol. 29, no. 2, pp. 245-262, 2019, doi:10.1142/S0218194019500116.

H. Hanif et al., "The rise of software vulnerability: Taxonomy of software vulnerabilities detection and machine learning approaches," J. Netw. Comput. Appl., vol. 179, p. 103009, 2021, doi:10.1016/j.jnca.2021.103009.

P. Sreekumari, "Malware detection techniques based on deep learning," in Proc. IEEE Int. Conf. Big Data Secur. Cloud, 2020, pp. 65-70, doi: 10.1109/BigDataSecurity-HPSC-IDS49724.2020.00023.

P. Maniriho, A. N. Mahmood, and M. J. M. Chowdhury, "A survey of recent advances in deep learning models for detecting malware in desktop and mobile platforms," ACM Comput. Surv., vol. 56, no. 6, pp. 1-41, 2023, doi: 10.1145/3638240.

P. Saraswathi et al., "An artificial intelligence approach for malware detection using deep learning," in Data Sci. Big Data Anal., 2023, pp. 583-599, doi: 10.1007/978-981-99-9179-2_44.

H. Naeem and A. Batool, "Malware attacks detection in network security using deep learning approaches," Int. J. Electron. Crime Investig., vol. 7, no. 3, pp. 31-44, 2023, doi:10.54692/ijeci.2023.0703160.

V. K. Borate et al., "Analysis of malware detection using various machine learning approach," Int. J. Adv. Res. Sci. Commun. Technol., vol. 4, no. 2, pp. 14-321, 2024.

S. Mohan, S. Babu, and B. Sahoo, "Deep learning-based malware detection," in Proc. Int. Conf. Comput. Commun. Netw. Technol. (ICCCNT), 2024, pp. 1-6, doi:10.1109/icccnt61001.2024.10724407.

R. Renugadevi et al., "Malware detection for Android systems using deep learning," in Proc. Int. Conf. Inventive Syst. Control (ICISC), 2024, pp. 67-72, doi: 10.1109/ICISC62624.2024.00018.

O. J. Falana et al., "Mal-Detect: An intelligent visualization approach for malware detection," J. King Saud Univ.-Comput. Inf. Sci., vol. 34, no. 5, pp. 1968-1983, 2022, doi: 10.1016/j.jksuci.2022.02.026.

A. L. Brown, M. Gupta, and M. Abdelsalam, "Automated machine learning for deep learning based malware detection," Comput. Secur., vol. 137, 2024, doi: 10.1016/j.cose.2023.103582.

A. Qamar, A. Karim, and V. Chang, "Mobile malware attacks: Review, taxonomy & future directions," Future Gener. Comput. Syst., vol. 97, pp. 887-909, Aug. 2019, doi: 10.1016/j.future.2019.03.007.

H. Eljak et al., "E-learning-based cloud computing environment: A systematic review, challenges, and opportunities," IEEE Access, vol. 12, pp. 7329-7355, 2024, doi: 10.1109/access.2023.3339250.

F. Wu, L. Xiao, and J. Zhu, "Bayesian model updating method based android malware detection for IoT services," in Proc. Int. Wireless Commun. Mobile Comput. Conf. (IWCMC), 2019, pp. 61-66, doi:10.1109/iwcmc.2019.8766754.

K. Sharma and B. B. Gupta, "Towards privacy risk analysis in android applications using machine learning approaches," Int. J. E-Services Mobile Appl., vol. 11, no. 2, pp. 1-21, Apr. 2019, doi:10.4018/ijesma.2019040101.

A. Feizollah et al., "AndroDialysis: Analysis of Android intent effectiveness in malware detection," Comput. Secur., vol. 65, pp. 121-134, Mar. 2017, doi: 10.1016/j.cose.2016.11.007.

M. A. Jerlin and K. Marimuthu, "A new malware detection system using machine learning techniques for API call sequences," J. Appl. Secur. Res., vol. 13, no. 1, pp. 45-62, Dec. 2017, doi:10.1080/19361610.2018.1387734.

R. Taheri et al., "Similarity-based Android malware detection using Hamming distance of static binary features," Future Gener. Comput. Syst., vol. 105, pp. 230-247, Apr. 2020, doi:10.1016/j.future.2019.11.034.

M. F. A. Razak et al., "Bio-inspired for features optimization and malware detection," Arab. J. Sci. Eng., vol. 43, no. 12, pp. 6963-6979, Nov. 2017, doi: 10.1007/s13369-017-2951-y.

M. Binjubier et al., "A GPU accelerated parallel genetic algorithm for the traveling salesman problem," J. Soft Comput. Data Min., vol. 5, no. 2, pp. 137-150, 2024, doi: 10.30880/jscdm.2024.05.02.010.

A. N. Yussuf et al., "Leveraging deep learning techniques for condition assessment of stormwater pipe network," J. Civ. Struct. Health Monit., vol. 15, no. 1, pp. 619-633, Aug. 2024, doi: 10.1007/s13349-024-00841-6.

J. Purohit and R. Dave, "Leveraging deep learning techniques to obtain efficacious segmentation results," Arch. Adv. Eng. Sci., vol. 1, no. 1, pp. 11-26, Jul. 2023, doi: 10.47852/bonviewAAES32021220.

Aswa, "AI-powered cybersecurity: Leveraging deep learning for real-time threat detection and prevention," Int. J. Eng. Comput. Sci., vol. 14, no. 1, pp. 26758-26772, Jan. 2025.

X. Chen et al., "Leveraging deep learning for automatic literature screening in intelligent bibliometrics," Int. J. Mach. Learn. Cybern., vol. 14, no. 4, pp. 1483-1525, Dec. 2022, doi: 10.1007/s13042-022-01710-8.

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors who publish with this journal agree to the following terms:

    1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
    2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
    3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).