Abstract
Neural networks are fragile because adversarial examples can readily assault them. As a result of the current scenario, academics from various countries have paid close attention to adversarial examples: many research outcomes, e.g., adversarial and defensive approaches and algorithms. However, numerous people are still baffled about how adversarial examples affect neural networks. We present hypotheses and devise extensive experiments to acquire more information about adversarial examples to verify this notion. By experiments, we investigate the neural network’s sensitivity to adversarial examples in diverse aspects, e.g., model architectures, activation functions, and loss functions. The consequence of the experiment shows that adversarial examples are closely related to them. Peculiarly, sensitivity’s property could help us distinguish the adversarial examples from the data set. This work will inspire the research of adversarial examples detection.
This work is supported by the National Science Foundation of China (Grant No. 62071275) and Shandong Province Key Innovation Project (Grant No. 2020CXGC010903 and Grant No. 2021SFGC0701).
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
Carlini, N., Wagner, D.A.: Towards evaluating the robustness of neural networks. In: 2017 IEEE Symposium on Security and Privacy (SP), pp. 39–57 (2017)
Clevert, D.A., Unterthiner, T., Hochreiter, S.: Fast and accurate deep network learning by exponential linear units (elus). arXiv: Learning (2016)
Contributors, T.: Logsigmoid (2019). https://pytorch.org/docs/stable/generated/torch.nn.LogSigmoid.html. Accessed on 23 Mar 2022
Contributors, T.: Softplus (2019). https://pytorch.org/docs/stable/generated/torch.nn.Softplus.html. Accessed on 23 Mar 2022
Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In: 2011 Proceedings of the 14th International Conference on Artificial Intelligence and Statisitics (AISTATS), vol. 15, pp. 315–323 (2011)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: International Conference on Learning Representations (ICLR) abs/1412.6572 (2015)
Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2261–2269 (2017). https://doi.org/10.1109/CVPR.2017.243
Ilyas, A., Santurkar, S., Tsipras, D., Engstrom, L., Tran, B., Madry, A.: Adversarial examples are not bugs, they are features. In: Advances in Neural Information Processing Systems abs/1905.02175, pp. 125–136 (2019)
Krizhevsky, A.: Learning multiple layers of features from tiny images. Technical report (2009)
Kurakin, A., Goodfellow, I.J., Bengio, S.: Adversarial examples in the physical world. Toulon, France (2017)
Lin, T.Y., Goyal, P., Girshick, R.B., He, K., Dollár, P.: Focal loss for dense object detection. IEEE Trans. Pattern Anal. Mach. Intell. 42, 318–327 (2020)
Liu, C., et al.: Defend against adversarial samples by using perceptual hash. Comput. Mater. Continua 62(3), 1365–1386 (2020)
Ma, X., et al.: Characterizing adversarial subspaces using local intrinsic dimensionality. In: International Conference on Learning Representations (2018). https://openreview.net/forum?id=B1gJ1L2aW
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. ArXiv abs/1706.06083 (2018)
Moosavi-Dezfooli, S.M., Fawzi, A., Frossard, P.: Deepfool: a simple and accurate method to fool deep neural networks. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 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 (2016)
Qin, Y., Carlini, N., Goodfellow, I.J., Cottrell, G., Raffel, C.: Imperceptible, robust, and targeted adversarial examples for automatic speech recognition, vol. 97, p. 5231–5240, California, USA, 09–15 June 2019
Raff, E., Sylvester, J., Forsyth, S., McLean, M.: Barrage of random transforms for adversarially robust defense. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6521–6530 (2019). https://doi.org/10.1109/CVPR.2019.00669
Pearl, R., Reed, L.J.: On the rate of growth of the population of the united states since 1790 and its mathematical representation. Proc. Nat. Acad. Sci. 6, 275–288 (1920)
Shannon, C.E.: A mathematical theory of communication. Bell Syst. Tech. J. 27, 379–423 (1948)
Szegedy, C., et al.: Intriguing properties of neural networks. In: International Conference on Learning Representations (ICLR) abs/1312.6199 (2014)
Wang, J., Dong, G., Sun, J., Wang, X., Zhang, P.: Adversarial sample detection for deep neural network through model mutation testing. In: 2019 IEEE/ACM 41st International Conference on Software Engineering (ICSE), pp. 1245–1256 (2019)
Xiao, C., Li, B., Zhu, J.Y., He, W., Liu, M., Song, D.X.: Generating adversarial examples with adversarial networks. ArXiv abs/1801.02610 (2018)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Yakura, H., Sakuma, J.: Robust audio adversarial example for a physical attack. In: International Joint Conference on Artificial Intelligence (IJCAI), vol. abs/1810.11793, Macao, China (2019)
Yang, Y., Zhang, G., Katabi, D., Xu, Z.: Me-net: towards effective adversarial robustness with matrix estimation, vol. 97, pp. 7025–7034. Long Beach, California, USA (2019)
Wu, Y., Arora, S.S., Wu, Y., Yang, H.: Beating attackers at their own games: Adversarial example detection using adversarial gradient directions. In: 35th AAAI Conference on Artificial Intelligence/33rd Conference on Innovative Applications of Artificial Intelligence/11th Symposium on Educational Advances in Artificial Intelligence, pp. 2969–2977 (2021)
Zhang, C., et al.: Interpreting and improving adversarial robustness of deep neural networks with neuron sensitivity. IEEE Trans. Image Process. 30, 1291–1304 (2021). https://doi.org/10.1109/TIP.2020.3042083
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhou, Z., Liu, J., Han, Y. (2022). Adversarial Examples Are Closely Relevant to Neural Network Models - A Preliminary Experiment Explore. In: Tan, Y., Shi, Y., Niu, B. (eds) Advances in Swarm Intelligence. ICSI 2022. Lecture Notes in Computer Science, vol 13345. Springer, Cham. https://doi.org/10.1007/978-3-031-09726-3_14
Download citation
DOI: https://doi.org/10.1007/978-3-031-09726-3_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-09725-6
Online ISBN: 978-3-031-09726-3
eBook Packages: Computer ScienceComputer Science (R0)