Abstract
Explainable Artificial Intelligence (XAI) techniques serve to bridge the gap between Learning based technique’s predictive performance and the model interpretability. In clinical domain, XAI is crucial for healthcare services deploying learning based techniques to retain patient’s trust and being accountable. Learning based techniques are susceptible to adversarial attacks which causes the model to misclassify. The article attempts to exercise XAI techniques as a measure to detect the effectiveness of the perturbations crafted by adversarial attacks on the trained model during run time. Frontline XAI techniques are explored to observe the possible perturbations crafted by Carlini and Wagner (CW) adversarial attack on a Recurrent Neural Network (RNN) trained using clinical informatics retrieved from Electronic Medical Records (EMR) for the binary classification task of Lung Cancer detection. The results manifest the authenticity of the suggested approach and provides guidelines for further research to utilize XAI to detect and reject adversarial samples.
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
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)
Kartoun, U.: Advancing informatics with electronic medical records bots (emrbots). Softw. Impacts 2, 100006 (2019)
Kelly, C.J., Karthikesalingam, A., Suleyman, M., Corrado, G., King, D.: Key challenges for delivering clinical impact with artificial intelligence. BMC Med. 17(1), 1–9 (2019)
Lipton, Z.C., Kale, D.C., Elkan, C., Wetzel, R.: Learning to diagnose with lstm recurrent neural networks. ArXiv preprint arXiv:1511.03677 (2015)
Ma, X., Niu, Y., Gu, L., Wang, Y., Zhao, Y., Bailey, J., Lu, F.: Understanding adversarial attacks on deep learning based medical image analysis systems. Pattern Recogn. 110, 107332 (2021)
Molnar, C.: Interpretable machine learning. Lulu, Com (2020)
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 (Euro S&P), pp. 372–387. IEEE (2016)
Papernot, N., McDaniel, P., Swami, A., Harang, R.: Crafting adversarial input sequences for recurrent neural networks. In: MILCOM 2016-2016 IEEE Military Communications Conference, pp. 49–54. IEEE (2016)
Rahman, A., Hossain, M.S., Alrajeh, N.A., Alsolami, F.: Adversarial examples–security threats to covid-19 deep learning systems in medical iot devices. IEEE Internet Things J. (2020)
Ribeiro, M.T., Singh, S., Guestrin, C.: Why should i trust you? Explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135–1144 (2016)
Wu, D., Fang, W., Zhang, Y., Yang, L., Luo, H., Ding, L., Xu, X., Yu, X.: Adversarial attacks and defenses in physiological computing: a systematic review. arXiv preprint arXiv:2102.02729 (2021)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Selvaganapathy, S., Sadasivam, S., Raj, N. (2022). SafeXAI: Explainable AI to Detect Adversarial Attacks in Electronic Medical Records. In: Satapathy, S.C., Peer, P., Tang, J., Bhateja, V., Ghosh, A. (eds) Intelligent Data Engineering and Analytics. Smart Innovation, Systems and Technologies, vol 266. Springer, Singapore. https://doi.org/10.1007/978-981-16-6624-7_50
Download citation
DOI: https://doi.org/10.1007/978-981-16-6624-7_50
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-6623-0
Online ISBN: 978-981-16-6624-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)