Abstract
Generative adversarial networks (GANs) have become one of the most popular research topics in deep learning. It is widely used in the term of image, and through the constant competition between generator and discriminator, it can generate so remarkably realistic images that human can’t distinguish. However, Although GAN has achieved great success in generating images, it is still in its infancy in generating adversarial malware examples. In this paper, we propose an PDF malware evasion method that is using GAN to generate adversarial PDF malware examples and evaluate it against four local machine learning based PDF malware classifiers. The evaluation is conducted on the same dataset which contains 100 malicious PDF files. The experimental results reveal that the proposed evasion attacks are effective, with attacks against three classifiers all attaining 100% evasion rate and attack against the last classifier also attaining 95% evasion rate on the evaluation dataset.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Symantec: Internet Security Threat Report, vol. 23 (2018)
Taigman, Y., Yang, M., Ranzato, M.A., Wolf, L.: DeepFace: closing the gap to human-level performance in face verification. In: CVPR (2014)
Vinyals, O., Kaiser, Ł., Koo, T., Petrov, S., Sutskever, I., Hinton, G.: Grammar as a foreign language. In: NIPS (2015)
He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: ICCV (2015)
Silver, D., et al.: Mastering the game of Go with deep neural networks and tree search. Nature 529, 484 (2016)
Maiorca, D., Ariu, D., Corona, I., Giacinto, G.: An evasion resilient approach to the detection of malicious PDF files. In: Camp, O., Weippl, E., Bidan, C., Aïmeur, E. (eds.) ICISSP 2015. CCIS, vol. 576, pp. 68–85. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-27668-7_5
Maiorca, D., Ariu, D., Corona, I., et al.: A structural and content-based approach for a precise and robust detection of malicious PDF files. In: 1st International Conference on Information Systems Security and Privacy (ICISSP 2015). IEEE (2015)
Smutz, C., Stavrou, A.: When a tree falls: using diversity in ensemble classifiers to identify evasion in malware detectors. In: 23rd Annual Network and Distributed System Security Symposium, NDSS 2016, San Diego, California, USA, 21–24 February 2016
Šrndić, N., Laskov, P.: Hidost: a static machine-learning-based detector of malicious files. EURASIP J. Inf. Secur. 2016(1), 22 (2016)
Biggio, B., Roli, F.: Wild patterns: ten years after the rise of adversarial machine learning. Pattern Recognit. (2017)
Biggio, B., et al.: Evasion attacks against machine learning at test time. In: Blockeel, H., Kersting, K., Nijssen, S., Železný, F. (eds.) ECML PKDD 2013. LNCS (LNAI), vol. 8190, pp. 387–402. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-40994-3_25
Biggio, B., et al.: Security evaluation of support vector machines in adversarial environments. In: Ma, Y., Guo, G. (eds.) Support Vector Machines Applications, pp. 105–153. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-02300-7_4
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. Comput. Sci. (2014)
Szegedy, C., Zaremba, W., Sutskever, I., et al.: Intriguing properties of neural networks. Comput. Sci. (2013)
Demontis, A., Melis, M., Biggio, B., et al.: Yes, machine learning can be more secure! A case study on android malware detection. IEEE Trans. Dependable Secur. Comput., 1 (2017)
Grosse, K., Papernot, N., Manoharan, P., Backes, M., McDaniel, P.: Adversarial Examples for Malware Detection. In: Foley, Simon N., Gollmann, D., Snekkenes, E. (eds.) ESORICS 2017. LNCS, vol. 10493, pp. 62–79. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-66399-9_4
Kolosnjaji, B., Demontis, A., Biggio, B., et al.: Adversarial malware binaries: evading deep learning for malware detection in executables (2018)
Wang, Q., et al.: In KDD 2017 - Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, vol. Part F129685, pp. 1145–1153. Association for Computing Machinery (2017)
Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., et al.: Generative adversarial nets. In: International Conference on Neural Information Processing Systems (2014)
Hu, W., Tan, Y.: Generating adversarial malware examples for black-box attacks based on GAN (2017)
Šrndić, N., Laskov, P.: Practical evasion of a learning-based classifier: a case study. In: IEEE S&P (2014)
Smutz, C., Stavrou, A.: Malicious PDF detection using metadata and structural features. In: ACM Press the 28th Annual Computer Security Applications Conference, Orlando, Florida, 03 December 2012–07 December 2012
Maiorca, D., Corona, I., Giacinto, G.: Looking at the bag is not enough to find the bomb: an evasion of structural methods for malicious PDF files detection. In: ACM SIGSAC Symposium on Information. ACM (2013)
Corona, I., Maiorca, D., Ariu, D., et al.: Lux0R: detection of malicious PDF-embedded JavaScript code through discriminant analysis of API references. In: Workshop on Artificial Intelligent & Security Workshop. ACM (2014)
Maiorca, D., Giacinto, G., Corona, I.: A Pattern Recognition System for Malicious PDF Files Detection. In: Perner, P. (ed.) MLDM 2012. LNCS (LNAI), vol. 7376, pp. 510–524. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-31537-4_40
Xu, W., Qi, Y., Evans, D.: Automatically evading classifiers: a case study on PDF malware classifiers. In: NDSS. The Internet Society (2016)
Acknowledgment
This work is supported by National Natural Science Foundation of China (No. 61876019 & U1636213).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, Y., Li, Y., Zhang, Q., Hu, J., Kuang, X. (2019). Evading PDF Malware Classifiers with Generative Adversarial Network. In: Vaidya, J., Zhang, X., Li, J. (eds) Cyberspace Safety and Security. CSS 2019. Lecture Notes in Computer Science(), vol 11982. Springer, Cham. https://doi.org/10.1007/978-3-030-37337-5_30
Download citation
DOI: https://doi.org/10.1007/978-3-030-37337-5_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-37336-8
Online ISBN: 978-3-030-37337-5
eBook Packages: Computer ScienceComputer Science (R0)