Abstract
This paper investigates the effectiveness of machine unlearning techniques in removing sensitive data from pre-trained Resnet-18 models using the CIFAR-10 dataset. Specifically, it compares the performance of Fine-Tuning and Fisher Noise-based Impair-Repair methods in minimizing data leakage and preserving model performance. The study evaluates the techniques’ ability to reduce Membership Inference Attack (MIA) scores while maintaining comparable accuracy on the retained data. The findings demonstrate that the Impair-Repair technique significantly reduces MIA scores compared to Fine-Tuning, showcasing its potential for responsible AI development. This approach allows for data privacy protection without compromising the model’s performance. The research contributes to advancing techniques that address the challenges of data privacy in machine learning.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Carlini, N., Chien, S., Nasr, M., Song, S., Terzis, A., Tramer, F.: Membership inference attacks from first principles. In: 2022 IEEE Symposium on Security and Privacy (SP), pp. 1897–1914. IEEE (2022)
Chen, M., Gao, W., Liu, G., Peng, K., Wang, C.: Boundary unlearning: rapid forgetting of deep networks via shifting the decision boundary. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7766–7775 (2023)
Doughan, Z., Al Mubasher, H., Kassem, R., El-Hajj, A.M., Haidar, A.M., Sliman, L.: Logic-based neural network for pattern correction. In: 2022 International Conference on Smart Systems and Power Management (IC2SPM), pp. 52–57. IEEE (2022)
Doughan, Z., Kassem, R., El-Hajj, A.M., Haidar, A.M.: Logic-based neural network for image compression applications. In: 2021 3rd IEEE Middle East and North Africa Communications Conference (MENACOMM), pp. 92–97. IEEE (2021)
Doughan, Z., Kassem, R., El-Hajj, A.M., Haidar, A.M.: Novel preprocessors for convolution neural networks. IEEE Access 10, 36834–36845 (2022)
Doughan, Z., Kassem, R., El-Hajj, A.M., Haidar, A.M.: Artificial neural network vision: between myth and reality. IEEE Potentials 42(3), 51–56 (2023)
Fariza, A., Arifin, A.Z.: Age estimation system using deep residual network classification method. In: 2019 International Electronics Symposium (IES), pp. 607–611. IEEE (2019)
Foster, J., Schoepf, S., Brintrup, A.: Fast machine unlearning without retraining through selective synaptic dampening. arXiv preprint: arXiv:2308.07707 (2023)
Liu, Y., Sun, C., Wu, Y., Zhou, A.: Unlearning with fisher masking. arXiv preprint: arXiv:2310.05331 (2023)
NEURIPS: unlearning-cifar10.ipynb. https://github.com/unlearning-challenge/starting-kit/blob/main/unlearning-CIFAR10.ipynb (2023). gitHub repository
Nguyen, T.T., Huynh, T.T., Nguyen, P.L., Liew, A.W.C., Yin, H., Nguyen, Q.V.H.: A survey of machine unlearning. arXiv preprint: arXiv:2209.02299 (2022)
Sekhari, A., Acharya, J., Kamath, G., Suresh, A.T.: Remember what you want to forget: algorithms for machine unlearning. In: Advances in Neural Information Processing Systems, vol. 34, pp. 18075–18086 (2021)
Shokri, R., Stronati, M., Song, C., Shmatikov, V.: Membership inference attacks against machine learning models. In: 2017 IEEE Symposium on Security and Privacy (SP), pp. 3–18. IEEE (2017)
Tarun, A.K., Chundawat, V.S., Mandal, M., Kankanhalli, M.: Deep regression unlearning. In: International Conference on Machine Learning, pp. 33921–33939. PMLR (2023)
Tarun, A.K., Chundawat, V.S., Mandal, M., Kankanhalli, M.: Fast yet effective machine unlearning. IEEE Trans. Neural Netw. Learn. Syst. (2023)
Thudi, A., Deza, G., Chandrasekaran, V., Papernot, N.: Unrolling SGD: understanding factors influencing machine unlearning. In: 2022 IEEE 7th European Symposium on Security and Privacy (EuroS &P), pp. 303–319. IEEE (2022)
Ullah, E., Mai, T., Rao, A., Rossi, R.A., Arora, R.: Machine unlearning via algorithmic stability. In: Conference on Learning Theory, pp. 4126–4142. PMLR (2021)
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 paper
Cite this paper
Doughan, Z., Itani, S. (2024). Machine Unlearning, A Comparative Analysis. In: Iliadis, L., Maglogiannis, I., Papaleonidas, A., Pimenidis, E., Jayne, C. (eds) Engineering Applications of Neural Networks. EANN 2024. Communications in Computer and Information Science, vol 2141. Springer, Cham. https://doi.org/10.1007/978-3-031-62495-7_42
Download citation
DOI: https://doi.org/10.1007/978-3-031-62495-7_42
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-62494-0
Online ISBN: 978-3-031-62495-7
eBook Packages: Computer ScienceComputer Science (R0)