Abstract
The use of Convolutional Neural Networks (CNNs) has brought significant benefits to the healthcare industry, enabling the successful execution of challenging tasks such as disease diagnosis and drug discovery. However, CNNs are vulnerable to various types of noise and attacks, including transmission noise, noisy mediums, truncated operations, and intentional poisoning attacks. To address these challenges, this paper proposes a robust recovery method that removes noise from potentially contaminated CNNs and offers an exact recovery guarantee for one-hidden-layer non-overlapping CNNs with the rectified linear unit (ReLU) activation function. The proposed method can recover both the weights and biases of the CNNs precisely, given some mild assumptions and an overparameterization setting. Our experimental results on synthetic data and the Wisconsin Diagnostic Breast Cancer (WDBC) dataset validate the efficacy of the proposed method. Additionally, we extend the method to eliminate poisoning attacks and demonstrate that it can be used as a defense strategy against malicious model poisoning.
H. Lu and Z. Huang—The first two authors contributed equally to this paper. This work was done when Hanxiao Lu and Zeyu Huang were research interns at the Trustworthy and Intelligent Machine Learning Research Group at the Illinois Institute of Technology.
R. Wang—This work was supported by the National Science Foundation (NSF) under Grant 2246157.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bai, J., Wang, R., Li, Z.: Physics-constrained backdoor attacks on power system fault localization. In: IEEE PES General Meeting (2023)
Dua, D., Graff, C.: UCI machine learning repository (2017). http://archive.ics.uci.edu/ml
Gao, C., Lafferty, J.: Model repair: robust recovery of over-parameterized statistical models. arXiv preprint arXiv:2005.09912 (2020)
Gu, T., Liu, K., Dolan-Gavitt, B., Garg, S.: BadNets: evaluating backdooring attacks on deep neural networks. IEEE Access 7, 47230–47244 (2019)
Gündüz, D., de Kerret, P., Sidiropoulos, N.D., Gesbert, D., Murthy, C.R., van der Schaar, M.: Machine learning in the air. IEEE J. Sel. Areas Commun. 37(10), 2184–2199 (2019)
Ismail, W.N., Hassan, M.M., Alsalamah, H.A., Fortino, G.: CNN-based health model for regular health factors analysis in internet-of-medical things environment. IEEE Access 8, 52541–52549 (2020). https://doi.org/10.1109/ACCESS.2020.2980938
Liu, C., et al.: TX-CNN: detecting tuberculosis in chest x-ray images using convolutional neural network. In: 2017 IEEE International Conference on Image Processing (ICIP), pp. 2314–2318 (2017). https://doi.org/10.1109/ICIP.2017.8296695
Ma, H., Guo, H., Lau, V.K.: Communication-efficient federated multitask learning over wireless networks. IEEE Internet Things J. 10(1), 609–624 (2022)
Pal, S., Wang, R., Yao, Y., Liu, S.: Towards understanding how self-training tolerates data backdoor poisoning. In: The AAAI’s Workshop on Artificial Intelligence Safety (2023)
Reshi, A.A., et al.: An efficient CNN model for COVID-19 disease detection based on x-ray image classification. Complex 2021, 6621607:1–6621607:12 (2021)
Shao, Y., Liew, S.C., Gunduz, D.: Denoising noisy neural networks: a Bayesian approach with compensation. arXiv preprint arXiv:2105.10699 (2021)
Wang, R., Zhang, G., Liu, S., Chen, P.-Y., Xiong, J., Wang, M.: Practical detection of trojan neural networks: data-limited and data-free cases. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12368, pp. 222–238. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58592-1_14
Zhong, K., Song, Z., Dhillon, I.S.: Learning non-overlapping convolutional neural networks with multiple kernels. arXiv preprint arXiv:1711.03440 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Lu, H., Huang, Z., Wang, R. (2023). Enhancing Healthcare Model Trustworthiness Through Theoretically Guaranteed One-Hidden-Layer CNN Purification. In: Chen, H., Luo, L. (eds) Trustworthy Machine Learning for Healthcare. TML4H 2023. Lecture Notes in Computer Science, vol 13932. Springer, Cham. https://doi.org/10.1007/978-3-031-39539-0_11
Download citation
DOI: https://doi.org/10.1007/978-3-031-39539-0_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-39538-3
Online ISBN: 978-3-031-39539-0
eBook Packages: Computer ScienceComputer Science (R0)