Abstract
Modern day smart cyber-physical systems (CPS) and Internet of Things (IoTs), including those deployed in critical devices such as wearables, often use embedded machine learning (ML). Owing to the consistent improvement in the overall performance of artificial neural networks (ANNs), the reliance of these systems on ANNs as an integral component has seen a constant rise. However, ANNs are known to be considerably vulnerable to noise. This, along with the noise being a ubiquitous component of the real-world environment, jeopardizes the accuracy of embedded ML-based systems. This calls for analyzing the impacts of noise on ANNs prior to their deployment in real-world ML-based system, to ensure acceptable ML accuracy.
This chapter deals with the issue of analyzing the impacts of noise on trained ANNs. Multiple approaches for studying the impacts and possible noise models are discussed. Various impacts of noise, along with their formalization, on trained ANNs are elaborated. The chapter also provides a suitable framework for analyzing the impacts of noise. To demonstrate the impact of noise on an ANN trained on real-world data quantitatively, the framework is then used for the analysis of a binary classifier trained on genetic attributes of Leukemia patients.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Botoeva, E., Kouvaros, P., Kronqvist, J., Lomuscio, A., Misener, R.: Efficient verification of ReLU-based neural networks via dependency analysis. In: Proc. AAAI (2020)
Bunel, R., Lu, J., Turkaslan, I., Kohli, P., Torr, P., Mudigonda, P.: Branch and bound for piecewise linear neural network verification. JMLR 21 (2020)
Carlini, N., Wagner, D.: Towards evaluating the robustness of neural networks. In: Symposium on Security and Privacy (SP), pp. 39–57. IEEE, Piscataway (2017)
Cheng, C.H., Nührenberg, G., Huang, C.H., Ruess, H.: Verification of binarized neural networks via inter-neuron factoring. In: Proc. VSTTE, pp. 279–290. Springer, Berlin (2018)
Dehnert, C., Junges, S., Katoen, J.P., Volk, M.: A storm is coming: a modern probabilistic model checker. In: International Conference on Computer Aided Verification, pp. 592–600. Springer, Berlin (2017)
Dutta, S., Jha, S., Sankaranarayanan, S., Tiwari, A.: Output range analysis for deep feedforward neural networks. In: Proc. NFM, pp. 121–138. Springer, Berlin (2018)
Esteva, A., Robicquet, A., Ramsundar, B., Kuleshov, V., DePristo, M., Chou, K., Cui, C., Corrado, G., Thrun, S., Dean, J.: A guide to deep learning in healthcare. Nat. Med. 25(1), 24 (2019)
Golub, T.R., Slonim, D.K., Tamayo, P., Huard, C., Gaasenbeek, M., Mesirov, J.P., Coller, H., Loh, M.L., Downing, J.R., Caligiuri, M.A., et al.: Molecular classification of cancer: class discovery and class prediction by gene expression monitoring. Science 286(5439), 531–537 (1999)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: Proc. ICLR (2015)
Huang, X., Kwiatkowska, M., Wang, S., Wu, M.: Safety verification of deep neural networks. In: Proc. CAV, pp. 3–29. Springer, Berlin (2017)
Katz, G., Barrett, C., Dill, D.L., Julian, K., Kochenderfer, M.J.: Reluplex: an efficient SMT solver for verifying deep neural networks. In: Proc. CAV, pp. 97–117. Springer, Berlin (2017)
Katz, G., Huang, D.A., Ibeling, D., Julian, K., Lazarus, C., Lim, R., Shah, P., Thakoor, S., Wu, H., Zeljić, A., et al.: The Marabou framework for verification and analysis of deep neural networks. In: International Conference on Computer Aided Verification, pp. 443–452. Springer, Berlin (2019)
Khalid, F., Ali, H., Hanif, M.A., Rehman, S., Ahmed, R., Shafique, M.: FaDec: a fast decision-based attack for adversarial machine learning. In: Proc. IJCNN, pp. 1–8. IEEE, Piscataway (2020)
Khalid, F., Hanif, M.A., Rehman, S., Ahmed, R., Shafique, M.: TrISec: training data-unaware imperceptible security attacks on deep neural networks. In: Proc. IOLTS. IEEE/ACM (2019)
Khalid, F., Hanif, M.A., Shafique, M.: Exploiting vulnerabilities in deep neural networks: adversarial and fault-injection attacks (2021). arXiv preprint arXiv:2105.03251
Khan, S., Ahmad, J., Naseem, I., Moinuddin, M.: A novel fractional gradient-based learning algorithm for recurrent neural networks. CSSP 37(2), 593–612 (2018)
Kurakin, A., Goodfellow, I., Bengio, S.: Adversarial examples in the physical world. In: International Conference on Learning Representations, ICLR, pp. 1–14 (2017)
Li, G., Yang, Y., Qu, X., Cao, D., Li, K.: A deep learning based image enhancement approach for autonomous driving at night. Knowl.-Based Syst. 213, 106617 (2021)
Moosavi-Dezfooli, S.M., Fawzi, A., Fawzi, O., Frossard, P.: Universal adversarial perturbations. In: Proc. CVPR, pp. 1765–1773 (2017)
Müller, M.N., Makarchuk, G., Singh, G., Püschel, M., Vechev, M.: PRIMA: general and precise neural network certification via scalable convex hull approximations. Proc. POPL 6(POPL), 1–33 (2022)
Nanda, V., Dooley, S., Singla, S., Feizi, S., Dickerson, J.P.: Fairness through robustness: investigating robustness disparity in deep learning. In: Proc. FAccT, pp. 466–477 (2021)
Narodytska, N., Kasiviswanathan, S.P., Ryzhyk, L., Sagiv, M., Walsh, T.: Verifying properties of binarized deep neural networks. In: Proc. AAAI, pp. 6615–6624 (2018)
Naseer, M., Minhas, M.F., Khalid, F., Hanif, M.A., Hasan, O., Shafique, M.: FANNet: Formal analysis of noise tolerance, training bias and input sensitivity in neural networks. In: Proc. DATE, pp. 666–669. IEEE, Piscataway (2020)
Papernot, N., McDaniel, P., Jha, S., Fredrikson, M., Celik, Z.B., Swami, A.: The limitations of deep learning in adversarial settings. In: Symposium on Security and Privacy (SP), pp. 372–387. IEEE, Piscataway (2016)
Pulina, L., Tacchella, A.: Challenging SMT solvers to verify neural networks. AI Commun. 25(2), 117–135 (2012)
Ratasich, D., Khalid, F., Geissler, F., Grosu, R., Shafique, M., Bartocci, E.: A roadmap toward the resilient Internet of Things for cyber-physical systems. IEEE Access 7, 13260–13283 (2019)
Shafique, M., Naseer, M., Theocharides, T., Kyrkou, C., Mutlu, O., Orosa, L., Choi, J.: Robust machine learning systems: Challenges, current trends, perspectives, and the road ahead. Design Test 37(2), 30–57 (2020)
Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., Fergus, R.: Intriguing properties of neural networks (2013). arXiv preprint arXiv:1312.6199
Tjeng, V., Xiao, K.Y., Tedrake, R.: Evaluating robustness of neural networks with mixed integer programming. In: Proc. ICLR (2019)
Tran, H.D., Pal, N., Musau, P., Lopez, D.M., Hamilton, N., Yang, X., Bak, S., Johnson, T.T.: Robustness verification of semantic segmentation neural networks using relaxed reachability. In: Proc. CAV, pp. 263–286. Springer, Berlin (2021)
Wang, S., Pei, K., Whitehouse, J., Yang, J., Jana, S.: Efficient formal safety analysis of neural networks. In: Proc. NeurIPS, pp. 6367–6377 (2018)
Wiyatno, R., Xu, A.: Maximal Jacobian-based saliency map attack (2018). arXiv preprint arXiv:1808.07945
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Naseer, M., Bhatti, I.T., Hasan, O., Shafique, M. (2024). Considering the Impact of Noise on Machine Learning Accuracy. In: Pasricha, S., Shafique, M. (eds) Embedded Machine Learning for Cyber-Physical, IoT, and Edge Computing. Springer, Cham. https://doi.org/10.1007/978-3-031-40677-5_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-40677-5_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-40676-8
Online ISBN: 978-3-031-40677-5
eBook Packages: EngineeringEngineering (R0)