Abstract
It is well known that Deep Neural Networks are vulnerable to adversarial examples. An adversary can inject carefully-crafted perturbations on clean input to manipulate the model output. In this paper, we propose a novel method, WED (Wavelet Extension and Denoising), to better resist adversarial examples. Specifically, WED adopts a wavelet transform to extend the input dimension with the image structures and basic elements. This can add significant difficulty for the adversary to calculate effective perturbations. WED further utilizes wavelet denoising to reduce the impact of adversarial perturbations on the model performance. Evaluations show that WED can resist 7 common adversarial attacks under both black-box and white-box scenarios. It outperforms two state-of-the-art wavelet-based approaches for both model accuracy and defense effectiveness.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Athalye, A., Carlini, N., Wagner, D.: Obfuscated gradients give a false sense of security: circumventing defenses to adversarial examples. In: Proceedings of the 35th International Conference on Machine Learning, ICML (2018)
Carlini, N., Wagner, D.: Towards evaluating the robustness of neural networks. In: 2017 IEEE Symposium on Security and Privacy (SP), pp. 39–57. IEEE (2017)
Chang, S.G., Yu, B., Vetterli, M.: Adaptive wavelet thresholding for image denoising and compression. IEEE Trans. Image Process. 9(9), 1532–1546 (2000)
Dong, Y., et al.: Boosting adversarial attacks with momentum. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9185–9193 (2018)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)
He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016, Part IV. LNCS, vol. 9908, pp. 630–645. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_38
Kurakin, A., Goodfellow, I., Bengio, S.: Adversarial examples in the physical world. arXiv preprint arXiv:1607.02533 (2016)
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083 (2017)
Moosavi-Dezfooli, S.M., Fawzi, A., Frossard, P.: Deepfool: a simple and accurate method to fool deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2574–2582 (2016)
Papernot, N., McDaniel, P., Jha, S., Fredrikson, M., Celik, Z.B., Swami, A.: The limitations of deep learning in adversarial settings. In: 2016 IEEE European Symposium on Security and Privacy (EuroS&P), pp. 372–387. IEEE (2016)
Papernot, N., McDaniel, P., Wu, X., Jha, S., Swami, A.: Distillation as a defense to adversarial perturbations against deep neural networks. In: 2016 IEEE Symposium on Security and Privacy (SP), pp. 582–597. IEEE (2016)
Prakash, A., Moran, N., Garber, S., DiLillo, A., Storer, J.: Deflecting adversarial attacks with pixel deflection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8571–8580 (2018)
Shaham, U., et al.: Defending against adversarial images using basis functions transformations. arXiv preprint arXiv:1803.10840 (2018)
Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034 (2013)
Szegedy, C., et al.: Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199 (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Zheng, Q., Qiu, H., Zhang, T., Memmi, G., Qiu, M., Lu, J. (2021). Resisting Adversarial Examples via Wavelet Extension and Denoising. In: Qiu, M. (eds) Smart Computing and Communication. SmartCom 2020. Lecture Notes in Computer Science(), vol 12608. Springer, Cham. https://doi.org/10.1007/978-3-030-74717-6_22
Download citation
DOI: https://doi.org/10.1007/978-3-030-74717-6_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-74716-9
Online ISBN: 978-3-030-74717-6
eBook Packages: Computer ScienceComputer Science (R0)