Intelligent Malware Adversarial Technology Based on Deep Learning

Yuefu Qiu; Kazem Chamran

doi:10.47297/taposatWSP2633-456953.20250608

PDF
导出
分享
收藏
专辑

Intelligent Malware Adversarial Technology Based on Deep Learning

6卷第8期

浏览量: 0 Downloads: 0

Intelligent Malware Adversarial Technology Based on Deep Learning
Intelligent Malware Adversarial Technology Based on Deep Learning
City University Malaysia, SintokKedah Darul Aman, 06010, Malaysia
2025年6卷第8期页码：279-283
纸质出版：2025-08-30
DOI：10.47297/taposatWSP2633-456953.20250608
Accepted：

Scan QR Code

(2025). Intelligent Malware Adversarial Technology Based on Deep Learning. 科技理论与实践（英文版）, 6(8), 279-283.

Qiu Yuefu,Chamran Kazem.Intelligent Malware Adversarial Technology Based on Deep Learning[J].Theory and Practice of Science and Technology,2025,06(08):279-283.
(2025). Intelligent Malware Adversarial Technology Based on Deep Learning. 科技理论与实践（英文版）, 6(8), 279-283. DOI： 10.47297/taposatWSP2633-456953.20250608.

Qiu Yuefu,Chamran Kazem.Intelligent Malware Adversarial Technology Based on Deep Learning[J].Theory and Practice of Science and Technology,2025,06(08):279-283. DOI： 10.47297/taposatWSP2633-456953.20250608.

摘要

Abstract

The continuous evolution of artificial intelligence (AI) and deep learning (DL) has reshaped the landscape of cybersecurity. This study explores the mechanisms

structures

and adversarial behaviors of intelligent malware that leverage AI models to evade traditional security systems. A comprehensive deep learning-based framework is proposed for malware detection

attack prediction

and defense optimization. Through empirical experiments using a hybrid dataset of 20

000 samples

our framework achieves 99.1% accuracy and demonstrates high robustness against adversarial perturbations. The study also highlights the vulnerability of DL models to adversarial attacks and backdoor threats

emphasizing the dual-use nature of AI technology. The results underscore the necessity of integrating explainable AI and federated defense mechanisms for next-generation cyber resilience.

关键词

Keywords

references

Hu W, Tan Y, Zhang L. MalGAN: Generative Adversarial Networks for Adversarial Malware[J]. IEEE Transactions on Information Forensics and Security, 2017, (10): 15–24.

Wang Q, Singh R, Chen H. DeepLocker: Concealing Attack Intent using Deep Learning[C]. Proceedings of the Black Hat Conference, 2018: 12–121.

Chen B, Zhao X, Li N. Adversarial Learning in Cybersecurity: Challenges and Advances[J]. Computers & Security, 2021, 14: 12–118.

Wang T, Liu P, Zhou D. Feature Extraction in Malware Analysis using CNN and RNN[J]. IEEE Access, 2022, 10: 12–55.

Rigaki M, Garcia S. GAN-based Traffic Imitation for Evasive Attacks[J]. Journal of Information Security, 2019, 10(2): 85–97.

Li N, Xu J, Sun F. Hybrid Deep Learning Models for Threat Prediction[J]. IEEE Transactions on Neural Networks and Learning Systems, 2020, 31(9): 54–66.