Abstract
Membership inference attacks are used as an audit tool to quantify training data leaks in machine learning models. Protection can be provided by anonymizing the training data or using training functions with differential privacy. Depending on the context, such as building data collection services for central machine learning models or responding to queries from end users, data scientists can choose between local and global differential privacy parameters. Different types of differential privacy have different epsilon values that reflect different mechanisms, making it difficult for data scientists to select appropriate differential privacy parameters and avoid inaccurate conclusions. The experiments in this paper show the relative privacy-accuracy trade-off of local and global differential privacy mechanisms under a white-box membership inference attack. While membership inference only reflects the lower bound for inference risk, and differential privacy formulates the upper bound, the experiments in this study with some datasets show that the trade-off between accuracy and privacy is similar for both types of mechanisms, although there is a large difference in their upper bounds. This suggests that the upper bound is far from the practical susceptibility to membership inference. Therefore, a small epsilon value in global differential privacy and a large epsilon value in local differential privacy lead to the same risk of membership inference. In addition, the risks from membership inference attacks are not uniform across all classes, especially when the training dataset in machine learning models is skewed.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Warner, S.L.: Randomized response: a survey technique for eliminating evasive answer bias. J. Am. Stat. Assoc. 60(309), 63–69 (1965)
Dwork, C., Kenthapadi, K., McSherry, F., Mironov, I., Naor, M.: Our data, ourselves: Privacy via distributed noise generation. In: Vaudenay, S. (ed.) EUROCRYPT 2006. LNCS, vol. 4004, pp. 486–503. Springer, Heidelberg (2006). https://doi.org/10.1007/11761679_29
Hill, K.: How target figured out a teen girl was pregnant before her father did. Forbes, Inc, vol. 7, pp.4–1 (2012)
Li, N., Qardaji, W., Su, D., Wu, Y., Yang, W.: Membership privacy: a unifying framework for privacy definitions. In: Proceedings of the 20th ACM SIGSAC Conference on Computer and Communications Security, pp. 889–900 (2013)
Fredrikson, M., Jha, S., Ristenpart, T.: Model inversion attacks that exploit confidence information and basic countermeasures. In: Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security, pp. 1322–1333 (2015)
Shokri, R., Shmatikov, V.: Privacy-preserving deep learning. In: Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security, pp. 1310–1321 (2015)
Tramèr, F., Zhang, F., Juels, A., Reiter, M.K., Ristenpart, T.: Stealing machine learning models via prediction {APIs}. In: Proceedings of the 25th USENIX Security Symposium, pp. 601–618 (2016)
Shokri, R., Stronati, M., Song, C., Shmatikov, V.: Membership inference attacks against machine learning models. In: Proceedings of the 38th IEEE Symposium on Security and Privacy, pp. 3–18 (2017)
Yeom, S., Giacomelli, I., Fredrikson, M., Jha, S.: Privacy risk in machine learning: analyzing the connection to overfitting. In: Proceedings of the IEEE 31st Computer Security Foundations Symposium (CSF), pp. 268–282 (2018)
Hayes, J., Melis, L., Danezis, G., De Cristofaro, E.: LOGAN: membership inference attacks against generative models. Proc. Priv. Enhancing Technol. (PoPETs) 2019(1), 133–152 (2019)
Hilprecht, B., Härterich, M., Bernau, D.: Monte Carlo and reconstruction membership inference attacks against generative models. Proc. Priv. Enhancing Technol. 2019(4), 232–249 (2019)
Jayaraman, B., Evans, D.: Evaluating differentially private machine learning in practice. In: Proceedings of the 28th USENIX Security Symposium (USENIX Security 2019), pp. 1895–1912 (2019)
Liu, K.S., Xiao, C., Li, B., Gao, J.: Performing co-membership attacks against deep generative models. In: Proceedings of the 19th IEEE International Conference on Data Mining (ICDM), pp. 459–467 (2019)
Nasr, M., Shokri, R., Houmansadr, A.: Comprehensive privacy analysis of deep learning. In: Proceedings of the 40th IEEE Symposium on Security and Privacy, pp. 1–15 (2019)
Nasr, M., Shokri, R., Houmansadr, A.: Comprehensive privacy analysis of deep learning: passive and active white-box inference attacks against centralized and federated learning. In: Proceedings of the 40th IEEE Symposium on Security and Privacy, pp. 739–753 (2019)
Salem, A., Zhang, Y., Humbert, M., Berrang, P., Fritz, M., Backes, M.: ML-leaks: model and data independent membership inference attacks and defenses on machine learning models. In: Proceedings of the 26th Network and Distributed Systems Security Symposium (2019)
Chen, D., Yu, N., Zhang, Y., Fritz, M.: GAN-leaks: a taxonomy of membership inference attacks against generative models. In: Proceedings of the 27th ACM SIGSAC Conference on Computer and Communications Security, pp. 343–362 (2020)
Ha, T., Dang, T.K., Le, H., Truong, T.A.: Security and privacy issues in deep learning: a brief review. SN Comput. Sci. 1(5), 253 (2020)
Leino, K., Fredrikson, M.: Stolen memories: leveraging model memorization for calibrated {White-Box} membership inference. In: Proceedings of the 29th USENIX Security Symposium (USENIX Security 20), pp. 1605–1622 (2020)
Long, Y., et al.: A pragmatic approach to membership inferences on machine learning models. In: Proceedings of the 5th IEEE European Symposium on Security and Privacy, pp. 521–534 (2020). https://doi.org/10.1109/EuroSP48549.2020.00040
Ha, T., Dang, T.K., Nguyen-Tan, N.: Comprehensive analysis of privacy in black-box and white-box inference attacks against generative adversarial network. In: Dang, T.K., Küng, J., Chung, T.M., Takizawa, M. (eds.) FDSE 2021. LNCS, vol. 13076, pp. 323–337. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-91387-8_21
Jayaraman, B., Wang, L., Knipmeyer, K., Gu, Q., Evans, D.: Revisiting membership inference under realistic assumptions. Proc. Priv. Enhancing Technol. 2021(2), 348–368 (2021). https://doi.org/10.2478/popets-2021-0031
Ha, T., Dang, T.K.: Inference attacks based on GAN in federated learning. Int. J. Web Inf. Syst. 18(2/3), 117–136 (2022)
Hu, H., Salcic, Z., Sun, L., Dobbie, G., Yu, P.S., Zhang, X.: Membership inference attacks on machine learning: a survey. ACM Comput. Surv. 54(11s), 1–37 (2022)
Liu, L., Wang, Y., Liu, G., Peng, K., Wang, C.: Membership inference attacks against machine learning models via prediction sensitivity. IEEE Trans. Dependable Secure Comput. 20(3), 2341–2347 (2022). https://doi.org/10.1109/TDSC.2022.3180828
Acknowledgements
This research is funded by University of Information Technology-Vietnam National University Ho Chi Minh City under grant number D1–2023-42.
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 Singapore Pte Ltd.
About this paper
Cite this paper
Ha, T., Vo, T., Dang, T.K., Trang, N.T.H. (2023). Differential Privacy Under Membership Inference Attacks. In: Dang, T.K., Küng, J., Chung, T.M. (eds) Future Data and Security Engineering. Big Data, Security and Privacy, Smart City and Industry 4.0 Applications. FDSE 2023. Communications in Computer and Information Science, vol 1925. Springer, Singapore. https://doi.org/10.1007/978-981-99-8296-7_18
Download citation
DOI: https://doi.org/10.1007/978-981-99-8296-7_18
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8295-0
Online ISBN: 978-981-99-8296-7
eBook Packages: Computer ScienceComputer Science (R0)