Abstract
With various benefits through software technology development, malicious attacks to steal confidential and company information have constantly been increasing. Recent deep learning models with images converted from malicious code achieve meaningful results, but they have challenges in classifying the same malware family, like Ramnit, Tracur, and Obfuscator. ACY that have similar structures in the image. Instead of observing the overall global features, there is a need for a method of considering the position of local features and learning the relationships between them. In this paper, we propose a vision transformer enhanced with the additional encoding of multiple patches for location information of local features and relationship information between them. For learning considering position information and all relationships between patches, [CLS] tokens that can summarize all information are utilized. 10-fold cross-validation with the Microsoft challenge dataset shows that the proposed model produces better accuracy than comparable studies. The misclassification analysis confirms that the proposed method can detect the same malware family penetrated by the conventional deep learning model. Additional analysis with the activation map emphasizes which structural and sequential features are extracted to detect different codes belonging to the same malware family.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Conti, G., Dean, E., Sinda, M., Sangster, B.: Visual reverse engineering of binary and data files. In: International Workshop on Visualization for Computer Security, pp. 1–17 (2008)
Nataraj, L., Karthikeyan, S., Jacob, G., Manjunath, B.S.: Malware images: visualization and automatic classification. In: Proceedings of the 8th International Symposium on Visualization for Cyber Security, pp. 1–7 (2011)
Kancherla, K., Mukkamala, S.: Image visualization based malware detection. In: IEEE Symposium on Computational Intelligence in Cyber Security (CICS), pp. 40–44 (2013)
Rezende, E., Ruppert, G., Carvalho, T., Ramos, F., De Geus, P.: Malicious software classification using transfer learning of resnet-50 deep neural network. In: 16th IEEE International Conference on Machine Learning and Applications (ICMLA), pp. 1011–1014 (2017)
Kalash, M., Rochan, M., Mohammed, N., Bruce, N.D., Wang, Y., Iqbal, F.: Malware classification with deep convolutional neural networks. In: 9th IFIP International Conference on New Technologies, Mobility and Security (NTMS), pp. 1–5 (2018)
Rezende, E., Ruppert, G., Carvalho, T., Theophilo, A., Ramos, F., Geus, P.D.: Malicious software classification using VGG16 deep neural network’s bottleneck features. In: Information Technology-New Generations, pp. 51–59 (2018)
Vasan, D., Alazab, M., Wassan, S., Safaei, B., Zheng, Q.: Image-based malware classification using ensemble of CNN architectures (IMCEC). Comput. Secur. 92, 101748 (2020)
Khan, R.U., Zhang, X., Kumar, R.: Analysis of ResNet and GoogleNet models for malware detection. J. Comput. Virol. Hack. Tech. 15(1), 29–37 (2019)
Cui, Z., Xue, F., Cai, X., Cao, Y., Wang, G.G., Chen, J.: Detection of malicious code variants based on deep learning. IEEE Trans. Ind. Inf. 14(7), 3187–3196 (2018)
Bhodia, N., Prajapati, P., Di Troia, F., Stamp, M.: Transfer learning for image-based malware classification. In: ICISSP (2019)
Su, J., Vasconcellos, D.V., Prasad, S., Sgandurra, D., Feng, Y., Sakurai, K.: Lightweight classification of IoT malware based on image recognition. In: IEEE 42Nd Annual Computer Software and Applications Conference (COMPSAC), vol. 2, pp. 664–669 (2018)
Yajamanam, S., Selvin, V.R.S., Di Troia, F., Stamp, M.: Deep learning versus gist descriptors for image-based malware classification. In: ICISSP, pp. 553–561 (2018)
Cui, Z., Du, L., Wang, P., Cai, X., Zhang, W.: Malicious code detection based on CNNs and multi-objective algorithm. J. Parallel Distrib. Comput. 129, 50–58 (2019)
Jung, B., Kim, T., Im, E.G.: Malware classification using byte sequence information. In: Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems, pp. 143–148 (2018)
Han, K., Lim, J.H., Im, E.G.: Malware analysis method using visualization of binary files. In: Proceedings of the 2013 Research in Adaptive and Convergent Systems, pp. 317–321 (2013)
Azab, A., Khasawneh, M.: MSIC: malware spectrogram image classification. IEEE Access 8, 102007–102021 (2020)
Li, L., Ding, Y., Li, B., Qiao, M., Ye, B.: Malware classification based on double byte feature encoding. Alexandria Eng. J. 61(1), 91–99 (2022)
Nataraj, L., Kirat, D., Manjunath, B.S., Vigna, G.: Sarvam: search and retrieval of malware. In: Proceedings of the Annual Computer Security Conference (ACSAC) Worshop on Next Generation Malware Attacks and Defense (NGMAD) (2013)
Kim, J.Y., Bu, S.J., Cho, S.B.: Malware detection using deep transferred generative adversarial networks. In: International Conference on Neural Information Proceedings, pp. 556–564 (2017)
Kim, J.Y., Bu, S.J., Cho, S.B.: Zero-day malware detection using transferred generative adversarial networks based on deep autoencoders. Inf. Sci. 460, 83–102 (2018)
Catak, F.O., Ahmed, J., Sahinbas, K., Khand, Z.H.: Data augmentation based malware detection using convolutional neural networks. PeerJ Comput. Sci. 7, e346 (2021)
Burks, R., Islam, K.A., Lu, Y., Li, J.: Data augmentation with generative models for improved malware detection: a comparative study. In: IEEE 10th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), pp. 660–665 (2019)
Lu, Y., Li, J.: Generative adversarial network for improving deep learning based malware classification. In: Winter Simulation Conference (WSC), pp. 584–593 (2019)
Yoo, S., Kim, S., Kang, B.B.: The image game: exploit kit detection based on recursive convolutional neural networks. IEEE Access 8, 18808–18821 (2020)
Choi, S., Jang, S., Kim, Y., Kim, J.: Malware detection using malware image and deep learning. In: International Conference on Information and Communication Technology Convergence (ICTC), pp. 1193–1195 (2017)
Kabanga, E.K., Kim, C.H.: Malware images classification using convolutional neural network. J. Comput. Commun. 6(1), 153–158 (2017)
Hsiao, S.C., Kao, D.Y., Liu, Z.Y., Tso, R.: Malware image classification using one-shot learning with siamese networks. Procedia Comput. Sci. 159, 1863–1871 (2019)
Zhu, J., Jang-Jaccard, J., Watters, P.A.: Multi-loss siamese neural network with batch normalization layer for malware detection. IEEE Access 8, 171542–171550 (2020)
Tobiyama, S., Yamaguchi, Y., Shimada, H., Ikuse, T., Yagi, T.: Malware detection with deep neural network using process behavior. In: IEEE 40th Annual Computer Software and Applications Conf. (COMPSAC), vol. 2, pp. 577–582 (2016)
Tran, T.K., Sato, H., Kubo, M.: Image-based unknown malware classification with few-shot learning models. In: International Symposium on Computing and Networking Workshops (CANDARW), pp. 401–407 (2019)
Kim, J.Y., Cho, S.B.: Detecting intrusive malware with a hybrid generative deep learning model. In: International Conference on Intelligent Data Engineering and Automated Learning, pp. 499–507 (2018)
Moti, Z., et al.: Generative adversarial network to detect unseen internet of things malware. Ad Hoc Netw. 122, 102591 (2021)
Jian, Y., Kuang, H., Ren, C., Ma, Z., Wang, H.: A novel framework for image-based malware detection with a deep neural network. Comput. Secur. 109, 102400 (2021)
Bhaskara, V.S., Bhattacharyya, D.: Emulating malware authors for proactive protection using GANs over a distributed image visualization of dynamic file behavior. arXiv preprint arXiv:1807.07525 (2018)
Yuan, B., Wang, J., Liu, D., Guo, W., Wu, P., Bao, X.: Byte-level malware classification based on markov images and deep learning. Comput. Secur. 92, 101740 (2020)
Dosovitskiy, A., et al.: An image is worth 16×16 words: transformers for image recognition at scale. In: ICLR (2021)
Ronen, R., Radu, M., Feuerstein, C., Yom-Tov, E., Ahmadi, M.: Microsoft malware classification challenge. arXiv preprint arXiv:1802.10135 (2018)
Jiang, Y., Chang, S., Wang, Z.: Transgan: two pure transformers can make one strong gan, and that can scale up. Adv. Neural Inf. Process. Syst. 34, 14745–14758 (2021)
Acknowledgement
This work was supported by an IITP grant funded by the Korean government (MSIT) (No. 2020–0-01361, Artificial Intelligence Graduate School Program (Yonsei University)) and Air Force Defense Research Sciences Program funded by Air Force Office of Scientific Research.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Park, KW., Cho, SB. (2022). A Vision Transformer Enhanced with Patch Encoding for Malware Classification. In: Yin, H., Camacho, D., Tino, P. (eds) Intelligent Data Engineering and Automated Learning – IDEAL 2022. IDEAL 2022. Lecture Notes in Computer Science, vol 13756. Springer, Cham. https://doi.org/10.1007/978-3-031-21753-1_29
Download citation
DOI: https://doi.org/10.1007/978-3-031-21753-1_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-21752-4
Online ISBN: 978-3-031-21753-1
eBook Packages: Computer ScienceComputer Science (R0)