Abstract
This paper shows a Min–Max property existing in the connection weights of the convolutional layers in a neural network structure, i.e., the LeNet. Specifically, the Min–Max property means that, during the back propagation-based training for LeNet, the weights of the convolutional layers will become far away from their centers of intervals, i.e., decreasing to their minimum or increasing to their maximum. From the perspective of uncertainty, we demonstrate that the Min–Max property corresponds to minimizing the fuzziness of the model parameters through a simplified formulation of convolution. It is experimentally confirmed that the model with the Min–Max property has a stronger adversarial robustness, thus this property can be incorporated into the design of loss function. This paper points out a changing tendency of uncertainty in the convolutional layers of LeNet structure, and gives some insights to the interpretability of convolution.
Similar content being viewed by others
References
Abbasi M, Gagné C (2017) Robustness to adversarial examples through an ensemble of specialists. In: Proceedings of the 5th international conference on learning representations (ICLR), Toulon, France, April 24–26, 2017
Athalye A, Carlini N, Wagner D (2018) Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples. In: Proceedings of the 35th international conference on machine learning (ICML), Stockholm, Sweden, July 10–15, 2018, pp 274–283
Basak J, De RK, Pal SK (1998) Unsupervised feature selection using a neuro-fuzzy approach. Pattern Recognit Lett 19(11):997–1006
Bradshaw J, Matthews AGdG, Ghahramani Z (2017) Adversarial examples, uncertainty, and transfer testing robustness in gaussian process hybrid deep networks. arXiv preprint arXiv:1707.02476
Brown TB, Mané D, Roy A, Abadi M, Gilmer J (2017) Adversarial patch. arXiv preprint arXiv:1712.09665
Carlini N, Wagner D (2017) Towards evaluating the robustness of neural networks. In: 2017 IEEE symposium on security and privacy (sp), pp 39–57. IEEE
Chen HY, Liang JH, Chang SC, Pan JY, Chen YT, Wei W, Juan DC (2019) Improving adversarial robustness via guided complement entropy. In: Proceedings of the IEEE international conference on computer vision, pp 4881–4889
Chen PY, Zhang H, Sharma Y, Yi J, Hsieh CJ (2017) Zoo: zeroth order optimization based black-box attacks to deep neural networks without training substitute models. In: Proceedings of the 10th ACM Workshop on artificial intelligence and security, pp 15–26
Clevert D, Unterthiner T, Hochreiter S (2016) Fast and accurate deep network learning by exponential linear units (elus). In: Bengio Y, LeCun Y (eds) 4th international conference on learning representations, ICLR 2016, San Juan, Puerto Rico, May 2–4, 2016, conference track proceedings. http://arxiv.org/abs/1511.07289
Deng L (2012) The mnist database of handwritten digit images for machine learning research [best of the web]. IEEE Signal Process Mag 29(6):141–142
Ding GW, Wang L, Jin X (2019) AdverTorch v0.1: an adversarial robustness toolbox based on pytorch. arXiv preprint arXiv:1902.07623
Dong Y, Liao F, Pang T, Su H, Zhu J, Hu X, Li J (2018) Boosting adversarial attacks with momentum. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 9185–9193
Eykholt K, Evtimov I, Fernandes E, Li B, Rahmati A, Xiao C, Prakash A, Kohno T, Song D (2018) Robust physical-world attacks on deep learning visual classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1625–1634
Glorot X, Bordes A, Bengio Y (2011) Deep sparse rectifier neural networks. In: Proceedings of the fourteenth international conference on artificial intelligence and statistics, pp 315–323
Goodfellow IJ, Shlens J, Szegedy C (2015) Explaining and harnessing adversarial examples. In: Bengio Y, LeCun Y (eds) 3rd international conference on learning representations, ICLR 2015, San Diego, CA, USA, May 7–9, 2015, conference track proceedings. http://arxiv.org/abs/1412.6572
Haykin S, Kosko B (2001) Gradient based learning applied to document recognition, pp 306–351
Hein M, Andriushchenko M (2017) Formal guarantees on the robustness of a classifier against adversarial manipulation. In: Advances in neural information processing systems, pp 2266–2276
Jia Y, Liu H, Hou J, Kwong S (2020) Pairwise constraint propagation with dual adversarial manifold regularization. IEEE Trans Neural Netw Learn Syst. https://doi.org/10.1109/TNNLS.2020.2970195
Jia Y, Liu H, Hou J, Kwong S (2020) Semisupervised adaptive symmetric non-negative matrix factorization. IEEE Trans Cybern. https://doi.org/10.1109/TCYB.2020.2969684
Karmon D, Zoran D, Goldberg Y (2018) Lavan: localized and visible adversarial noise. In: Dy JG, Krause A (eds) Proceedings of the 35th international conference on machine learning, ICML 2018, Stockholmsmässan, Stockholm, Sweden, July 10–15, 2018, Proceedings of Machine Learning Research, vol. 80, pp 2512–2520. PMLR. http://proceedings.mlr.press/v80/karmon18a.html
Krippendorff K (2009) Figure 12 in Klaus Krippendorff’s ’ross Ashby’s information theory: a bit of history, some solutions to problems, and what we face today. Int J Gen Syst 38:189–212. https://doi.org/10.1080/03081070902993178(Int. J. Gen. Syst. 38(6), 667–668 (2009))
Krizhevsky A, Hinton G et al (2009) Learning multiple layers of features from tiny images
Kurakin A, Goodfellow IJ, Bengio S (2017) Adversarial examples in the physical world. In: Proceedings of the 5th international conference on learning representations (ICLR), Toulon, France, April 24–26, 2017
Kurakin A, Goodfellow IJ, Bengio S (2017) Adversarial machine learning at scale. In: 5th International conference on learning representations, ICLR 2017, Toulon, France, April 24–26, 2017, conference track proceedings. OpenReview.net. https://openreview.net/forum?id=HJGU3Rodl
Lin J (1991) Divergence measures based on the Shannon entropy. IEEE Trans Inf Theory 37(1):145–151
Liu H, Ji R, Li J, Zhang B, Gao Y, Wu Y, Huang F (2019) Universal adversarial perturbation via prior driven uncertainty approximation. In: Proceedings of the IEEE/CVF international conference on computer vision (ICCV)
Liu H, Jia Y, Hou J, Zhang Q (2019) Imbalance-aware pairwise constraint propagation. In: Proceedings of the 27th ACM international conference on multimedia, pp 1605–1613
Liu X, Yang H, Liu Z, Song L, Chen Y, Li H (2019) DPATCH: an adversarial patch attack on object detectors. In: Proceedings of the AAAI workshop on artificial intelligence safety (SafeAI), Honolulu, Hawaii, USA, January 27, 2019
Liu Y, Chen X, Liu C, Song D (2016) Delving into transferable adversarial examples and black-box attacks. arXiv preprint. https://arxiv.org/abs/1611.02770
Madry A, Makelov A, Schmidt L, Tsipras D, Vladu A (2018) Towards deep learning models resistant to adversarial attacks. In: Proceedings of the 6th international conference on learning representations (ICLR), Vancouver, BC, Canada, April 30–May 3, 2018
Mishkin D, Matas J (2016) All you need is a good init. In: Bengio Y, LeCun Y (eds) 4th International conference on learning representations, ICLR 2016, San Juan, Puerto Rico, May 2–4, 2016, conference track proceedings. http://arxiv.org/abs/1511.06422
Moosavi-Dezfooli SM, Fawzi A, Frossard P (2016) 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
Papernot N, McDaniel P, Goodfellow I (2016) Transferability in machine learning: from phenomena to black-box attacks using adversarial samples. arXiv preprint arXiv:1605.07277
Papernot N, McDaniel P, Jha S, Fredrikson M, Celik ZB, Swami A (2016) The limitations of deep learning in adversarial settings. In: 2016 IEEE European symposium on security and privacy (EuroS&P), pp. 372–387. IEEE
Papernot N, McDaniel P, Wu X, Jha S, Swami A (2016) Distillation as a defense to adversarial perturbations against deep neural networks. In: 2016 IEEE symposium on security and privacy (SP), pp 582–597. IEEE
Pinto L, Davidson J, Sukthankar R, Gupta A (2017) Robust adversarial reinforcement learning. In: Proceedings of the 34th international conference on machine learning (ICML), Sydney, NSW, Australia, August 6–11, 2017
Pourpanah F, Abdar M, Luo Y, Zhou X, Wang R, Lim CP, Wang XZ (2020) A review of generalized zero-shot learning methods. arXiv preprint arXiv:2011.08641
Qin C, Martens J, Gowal S, Krishnan D, Dvijotham K, Fawzi A, De S, Stanforth R, Kohli P (2019) Adversarial robustness through local linearization. In: Advances in neural information processing systems, pp 13847–13856
Raghunathan A, Steinhardt J, Liang P (2018) Certified defenses against adversarial examples. In: Proceedings of the 6th international conference on learning representations (ICLR), Vancouver, BC, Canada, April 30–May 3, 2018
Seeger M (2004) Gaussian processes for machine learning. Int J Neural Syst 14(02):69–106
Shannon CE (2001) A mathematical theory of communication. ACM SIGMOBILE Mobile Comput Commun Rev 5(1):3–55
Sharif M, Bhagavatula S, Bauer L, Reiter MK (2016) Accessorize to a crime: Real and stealthy attacks on state-of-the-art face recognition. In: Proceedings of the 2016 ACM sigsac conference on computer and communications security, pp 1528–1540
Shen H, Chen S, Wang R, Wang X (2020) Generalized adversarial examples: Attacks and defenses. arXiv preprint arXiv:2011.14045
Sinha A, Namkoong H, Duchi JC (2018) Certifying some distributional robustness with principled adversarial training. In: Proceedings of the 6th international conference on learning representations (ICLR), Vancouver, BC, Canada, April 30–May 3, 2018
Smith L, Gal Y (2018) Understanding measures of uncertainty for adversarial example detection. In: Proceedings of the 34th conference on uncertainty in artificial intelligence (UAI), Monterey, California, USA, August 6–10, 2018, pp 560–569
Springenberg JT, Dosovitskiy A, Brox T, Riedmiller MA (2015) Striving for simplicity: The all convolutional net. In: Bengio Y, LeCun Y (eds) 3rd International conference on learning representations, ICLR 2015, San Diego, CA, USA, May 7–9, 2015, workshop track proceedings. http://auai.org/uai2018/proceedings/papers/207.pdf
Su D, Zhang H, Chen H, Yi J, Chen PY, Gao Y (2018) Is robustness the cost of accuracy?—a comprehensive study on the robustness of 18 deep image classification models. In: Proceedings of the European conference on computer vision (ECCV), pp 631–648
Su J, Vargas DV, Sakurai K (2019) One pixel attack for fooling deep neural networks. IEEE Trans Evolut Comput 23(5):828–841
Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2818–2826
Szegedy C, Zaremba W, Sutskever I, Bruna J, Erhan D, Goodfellow IJ, Fergus R (2014) Intriguing properties of neural networks. In: Bengio Y, LeCun Y (eds) 2nd international conference on learning representations, ICLR 2014, Banff, AB, Canada, April 14–16, 2014, conference track proceedings. http://arxiv.org/abs/1312.6199
Terzi M, Susto GA, Chaudhari P (2020) Directional adversarial training for cost sensitive deep learning classification applications. Eng Appl Artif Intell 91:103550
Tramér F, Kurakin A, Papernot N, Goodfellow IJ, Boneh D, McDaniel PD (2018) Ensemble adversarial training: Attacks and defenses. In: Proceedings of the 6th international conference on learning representations (ICLR), Vancouver, BC, Canada, April 30–May 3, 2018
Tsipras D, Santurkar S, Engstrom L, Turne, A, Madry A(2019) Robustness may be at odds with accuracy. In: Proceedings of the 7th international conference on learning representations (ICLR), New Orleans, LA, USA, May 6–9, 2019
Wong E, Kolter JZ (2018) Provable defenses against adversarial examples via the convex outer adversarial polytope. In: Proceedings of the 35th international conference on machine learning (ICML), Stockholm, Sweden, July 10–15, 2018, pp 8405–8423
Xiao H, Rasul K, Vollgraf R (2017) Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms
Yeung DS, Wang X (2002) Improving performance of similarity-based clustering by feature weight learning. IEEE Trans Pattern Anal Mach Intell 24(4):556–561
Zhang H, Yu Y, Jiao J, Xing EP, Ghaoui LE, Jordan MI (2019) Theoretically principled trade-off between robustness and accuracy. In: Proceedings of the 36th international conference on machine learning (ICML), Long Beach, California, USA, June 9–15, 2019, pp 12907–12929
Zhao Z, Dua D, Singh S (2018) Generating natural adversarial examples. In: Proceedings of the 6th international conference on learning representations (ICLR), Vancouver, BC, Canada, April 30–May 3, 2018
Acknowledgements
This work was supported in part by Natural Science Foundation of China (Grants 61732011 and 61976141, 61772344), in part by the Natural Science Foundation of SZU (827-000230), in part by the Interdisciplinary Innovation Team of Shenzhen University, and in part by Natural Science Foundation of Guangdong Province of China (Grant 2020B1515310008).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that there is no conflict of interests regarding the publication of this article.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Shen, H., Chen, S. & Wang, R. A study on the uncertainty of convolutional layers in deep neural networks. Int. J. Mach. Learn. & Cyber. 12, 1853–1865 (2021). https://doi.org/10.1007/s13042-021-01278-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-021-01278-9