Generative Adversarial Networks for Anomaly and Malware Detection
DOI:
https://doi.org/10.69968/ijisem.2026v5i3416-425Keywords:
Generative Adversarial Networks (GANs), mal-ware detection, cyber setting, deep neural networksAbstract
Generative Adversarial Networks or GANs, have become a significant approach in deep learning along with Con-volutional and Recurrent Neural Networks, due to improvements in computing technology and more advanced ways to train these frameworks or models. Since GANs were first introduced in 2014, their application has expanded beyond image generation to include critical security tasks like anomaly detection and malware analysis. This paper offers a comprehensive survey of how GAN-based methods are utilized for identifying unusual and harmful activities in cyber settings. It examines key variants of GANs relevant to this field, explains their fundamental architectures and training methods, and explains their integration into systems to detect anomalies and malware. Additionally, the paper catalogs publicly accessible datasets and evaluation metrics frequently used in the reviewed studies to illustrate common experimental methodologies and research directions. Finally, it addresses ongoing challenges and potential future avenues for employing GANs to counteract emerging cybersecurity threats, highlighting their importance in developing more proactive and robust security measures.
References
[1] Bayer et al. “Dynamic Analysis of Malicious Code” vol. 2, pp. 66-67, 2006; Doi: 10.1007/s11416-006-0012-2.
[2] Petrosyan, “Annual number of malware attacks worldwide from 2015 to 2022” 2023. Online, Accessed 2 2 2024.
[3] N. J. Palatty “30+ Malware Statistics You Need To Know In 2024” Astra, 2023. Online, Accessed 2 2 2024.
[4] J. Brownlee, “How to develop an auxiliary classifier GAN (AC-GAN) from scratch with Keras” 2021. Online, Accessed 2 2 2024.
[5] Dunmore et al. “Generative Adversarial Networks for Malware Detection: a Survey” ArXiv, vol. abs/2302.08558, 2023; Doi: 10.48550/arXiv.2302.08558.
[6] S. Gihon, “Ransomware Trends Q4 2023 Report” 2024. Online, Ac-cessed 2 2 2024.
[7] W. Hu and Y. Tan, “Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN” ArXiv, vol. abs/1702.05983, 2017.
[8] Salimans et al. “Improved Techniques for Training GANs” ArXiv, vol. abs/1606.03498, 2016.
[9] Isola et al. “Image-to-Image Translation with Conditional Adver-sarial Networks” in 2017 IEEE Conference on Computer Vi-sion and Pattern Recognition (CVPR), 2017, pp. 5967-5976; Doi: 10.1109/CVPR.2017.632.
[10] J. Ho and S. Ermon, “Generative Adversarial Imitation Learning” in Neural Information Processing Systems 2016.
[11] Gharakhanian, “Generative Adversarial Networks – Hot Topic in Machine Learning” 2017. Online, Accessed 2 2 2024.
[12] He et al. “Analysis of Image Generation by different Generator in GANs” Journal of Physics: Conference Series, vol. 1903, 2021.
[13] Radford et al. “Unsupervised Representation Learning with Deep Convo-lutional Generative Adversarial Networks” CoRR, vol. abs/1511.06434, 2015.
[14] Goodfellow et al. “Generative Adversarial Nets” in Neural Information Processing Systems, 2014.
[15] M. Arjovsky and L. Bottou, “Towards Principled Methods for Training Generative Adversarial Networks” ArXiv, vol. abs/1701.04862, 2017.
[16] Cai et al. “Generative Adversarial Networks” ACM Computing Surveys (CSUR), vol. 54, pp. 1-38, 2021.
[17] Navidan et al. “Generative Adversarial Networks (GANs) in Net-working: A Comprehensive Survey & Evaluation” ArXiv, vol. abs/2105.04184, 2021.
[18] Won et al. “PlausMal-GAN: Plausible Malware Training Based on Generative Adversarial Networks for Analogous Zero-Day Malware Detection” IEEE Transactions on Emerging Topics in Computing, vol. 11, pp. 82-94, 2023; Doi: 10.1109/TETC.2022.3170544.
[19] Dutta et al. “Generative Adversarial Networks in Security: A Survey” 2020. 11th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), pp. 0399-0405, 2020.
[20] Prabakaran et al. “An enhanced deep learning-based phishing detection mechanism to effectively identify malicious URLs using variational autoencoders” IET Information Security, vol. 17, no. 3, pp. 315-551, 2023; Doi: 10.1049/ise2.12106.
[21] Salimans et al. “Improved Techniques for Training GANs” ArXiv, vol. abs/1606.03498, 2016.
[22] S. T. Barratt and S. Rishi, “A Note on the Inception Score” ArXiv, vol. abs/1801.01973, 2018.
[23] Borji, “Pros and Cons of GAN Evaluation Measures” ArXiv, vol. abs/1802.03446, 2018.
[24] Dunmore et al. “A Comprehensive Survey of Generative Adversarial Networks (GANs) in Cybersecurity Intrusion Detection” IEEE Access, vol. 11, pp. 76071-76094, 2023; Doi: 10.1109/ACCESS.2023.3296707.
[25] Che et al. “Mode Regularized Generative Adversarial Networks” ArXiv, vol. abs/1612.02136, 2017.
[26] Szegedy et al. “Rethinking the Inception Architecture for Computer Vi-sion” in 2016 IEEE Conference on Computer Vision and Pattern Recog-nition (CVPR), 2016, pp. 2818-2826; Doi: 10.1109/CVPR.2016.308.
[27] Rohra et al.“User Localization in an Indoor Environment Using Fuzzy Hybrid of Particle Swarm Optimization & Gravitational Search Al-gorithm with Neural Networks” in International Conference on Soft Computing for Problem Solving, 2016.
[28] Meneghello et al. “A CSI Dataset for Wireless Human Sensing on 80 MHz Wi-Fi Channels” IEEE Communications Magazine, vol. 61, pp. 146-152, 2023.
[29] Yousefi et al. “A Survey on Behavior Recognition Using WiFi Channel State Information” IEEE Communications Magazine, vol. 55, pp. 98-104, 2017.
[30] Ronen et al. “Microsoft Malware Classification Challenge” ArXiv, vol. abs/1802.10135, 2018.
[31] Nataraj et al. “Malware images: visualization and automatic classifica-tion” in Visualization for Computer Security, 2011.
[32] M. Mirza and S. Osindero “Conditional Generative Adversarial Nets” ArXiv, vol. abs/1411.1784, 2014.
[33] Chen et al. “InfoGAN: Interpretable Representation Learning by Infor-mation Maximizing Generative Adversarial Nets” in Neural Information Processing Systems, 2016.
[34] Li et al. “SCGAN: Disentangled Representation Learning by Adding Similarity Constraint on Generative Adversarial Nets” IEEE Access, vol. 7, pp. 147928-147938, 2019.
[35] Zhu et al. “Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks” IEEE International Conference on Computer Vision (ICCV), pp. 2242-2251, 2017.
[36] Isola et al. “Image-to-Image Translation with Conditional Ad-versarial Networks” 2017 IEEE Conference on Computer Vi-sion and Pattern Recognition (CVPR), pp. 5967-5976, 2016; Doi: 10.1109/CVPR.2017.632.
[37] Odena et al. “Conditional Image Synthesis with Auxiliary Classifier GANs” in International Conference on Machine Learning, 2016.
[38] R. Nagaraju and M. Stamp “Auxiliary-Classifier GAN for Malware Analysis” ArXiv, vol. abs/2107.01620, 2021.
[39] Donahue et al. “Adversarial Feature Learning” ArXiv, vol. abs/1605.09782, 2016.
[40] Xu et al. “Improved bidirectional GAN-based approach for network intrusion detection using one-class classifier” MDPI (Basel, Switzerland) 2022; Doi: 10.3390/computers 11060085.
[41] Saito et al. “Temporal Generative Adversarial Nets with Singular Value Clipping” in 2017. IEEE International Conference on Computer Vision (ICCV), 2017, pp. 2849-2858; Doi: 10.1109/ICCV.2017.308.
[42] Munoz et al. “Multi-Variate Temporal GAN for Large Scale Video Generation” ArXiv, vol. abs/2004.01823, 2020.
[43] Mao et al. “Least Squares Generative Adversarial Networks” in 2017. IEEE International Conference on Computer Vision (ICCV), 2017, pp. 2813-2821; Doi: 10.1109/ICCV.2017.304.
[44] Arjovsky et al. ”Wasserstein GAN,” ArXiv, vol. abs/1701.07875.
[45] Gulrajani et al. “Improved Training of Wasserstein GANs” in Neural Information Processing Systems, 2017.
[46] Wang et al. ”Evolutionary Generative Adversarial Networks” IEEE Transactions on Evolutionary Computation, vol. 23, pp. 921-934, 2019; Doi:10.1109/TEVC.2019.2895748
[47] Berthelot, et al. “BEGAN: Boundary Equilibrium Generative Adversar-ial Networks” ArXiv, vol. abs/1703. 10717, 2017.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Amit Kumar Thakore, Neha Gupta, Akash Saxena, Amar Singh Verma
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Re-users must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use. This license allows for redistribution, commercial and non-commercial, as long as the original work is properly credited.
How to Cite
7
