Yet another research on GANs in cybersecurity

• Authors: Michał Zimoń , Rafał Kasprzyk

Abstracts

EN

Deep learning algorithms have achieved remarkable results in a wide range of tasks, including image classification, language translation, speech recognition, and cybersecurity. These algorithms can learn complex patterns and relationships from large amounts of data, making them highly effective for many applications. However, it is important to recognize that models built using deep learning are not fool proof and can be fooled by carefully crafted input samples. This paper presents the results of a study to explore the use of Generative Adversarial Networks (GANs) in cyber security. The results obtained confirm that GANs enable the generation of synthetic malware samples that can be used to mislead a classification model.

Keywords

EN

cybersecurity; malware; artificial intelligence; machine learning; deep learning; generative adversarial networks

• Publisher: Akademia Sztuki Wojennej
• Journal: Cybersecurity and Law
• Year: 2023
• Volume: 9
• Issue: 1
• Pages: 61-72

Dates

published

2023

Contributors

author

Michał Zimoń

• Faculty of Cybernetics, Military University of Technology, Warsaw

author

Rafał Kasprzyk

• Faculty of Cybernetics, Military University of Technology, Warsaw

References

• Bozkir A.S., Cankaya, A.O., Aydos M., Utilization and Comparision of Convolutional Neural Networks in Malware Recognition, 2019, https://www.researchgate.net/publication/331773587_Utilization_and_Comparision_of_Convolutional_Neural_Networks_in_Malware_Recognition [access: 4.01.2023].
• He K., Zhang X., Ren S., Sun J., Deep Residual Learning for Image Recognition, 2015, https://arxiv.org/pdf/1512.03385.pdf [access: 4.01.2023].
• Karras T. et al., Training Generative Adversarial Networks with Limited Data, 2020, https://arxiv.org/pdf/2006.06676.pdf [access: 4.01.2023].
• Radford A., Metz L., Chintala S., Unsupervised Represenation Learning With Deep Convolutional Generative Aadversarial Networks, 2016, https://arxiv.org/pdf/1511.06434.pdf [access:4.01.2023].
• Salian I., NVIDIA Research Achieves AI Training Breakthrough, 2020, https://blogs.nvidia.com/blog/2020/12/07/neurips-research-limited-data-gan/ [access: 4.01.2023].
• Tan M., Le Q., EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks, 2019, https://arxiv.org/pdf/1905.11946.pdf [access: 4.01.2023].

Identifiers

DOI

10.35467/cal/169299

Biblioteka Nauki

13946602