Bits for Privacy: Evaluating Post-Training Quantization via Membership Inference

ZHANG, Chenxiang; Qu, Tongxi; Li, Zhong; Zhang, Tian; PANG, Jun; MAUW, Sjouke

doi:10.1109/trustcom66490.2025.00099

Request a copy

Paper published in a book (Scientific congresses, symposiums and conference proceedings)

Bits for Privacy: Evaluating Post-Training Quantization via Membership Inference

ZHANG, Chenxiang; Qu, Tongxi; Li, Zhong et al.

2025 • In Proceedings of 24th IEEE International Conference On Trust, Security And Privacy In Computing And Communications

Peer reviewed

Permalink
https://hdl.handle.net/10993/67863

DOI
10.1109/trustcom66490.2025.00099

Files (1)Send to Details Statistics Bibliography Similar publications

Files

Full Text

Bits_for_Privacy_Evaluating_Post-Training_Quantization_via_Membership_Inference.pdf

Publisher postprint (1.02 MB)

Request a copy

All documents in ORBilu are protected by a user license.

Send to

RIS BibTex APA Chicago Permalink X Linkedin

Details

Disciplines :

Computer science

Author, co-author :

ZHANG, Chenxiang ; University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS)

Qu, Tongxi; Nanjing University,Department of Computer Science,Nanjing,China

Li, Zhong; Nanjing University,Department of Computer Science,Nanjing,China

Zhang, Tian; Nanjing University,Department of Computer Science,Nanjing,China

PANG, Jun ; University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS)

MAUW, Sjouke ; University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS)

External co-authors :

yes

Language :

English

Title :

Bits for Privacy: Evaluating Post-Training Quantization via Membership Inference

Publication date :

14 November 2025

Event name :

24th IEEE International Conference On Trust, Security And Privacy In Computing And Communications

Event date :

2025

Audience :

International

Main work title :

Proceedings of 24th IEEE International Conference On Trust, Security And Privacy In Computing And Communications

Publisher :

IEEE CS

Peer reviewed :

Peer reviewed

Additional URL :

http://xplorestaging.ieee.org/ielx8/11354467/11354567/11354754.pdf?arnumber=11354754

Available on ORBilu :

since 24 February 2026

Statistics

Number of views

44 (0 by Unilu)

Number of downloads

0 (0 by Unilu)

More statistics

Scopus citations^®

Scopus citations^®
without self-citations

OpenCitations

OpenAlex citations

Bibliography

I. Hubara, M. Courbariaux, D. Soudry, R. El-Yaniv, and Y. Bengio, "Quantized neural networks: Training neural networks with low precision weights and activations, " Journal of Machine Learning Research, vol. 18, no. 187, pp. 1-30, 2018.
M. T. Lê, P. Wolinski, and J. Arbel, "Efficient neural networks for tiny machine learning: A comprehensive review, " arXiv preprint arXiv: 2311. 11883, 2023.
A. Gholami, S. Kim, Z. Dong, Z. Yao, M. W. Mahoney, and K. Keutzer, "A survey of quantization methods for efficient neural network inference, " in Low-power Computer Vision, 2022, pp. 291-326.
M. Nagel, M. Fournarakis, R. A. Amjad, Y. Bondarenko, M. Van Baalen, and T. Blankevoort, "A white paper on neural network quantization, " arXiv preprint arXiv: 2106. 08295, 2021.
S. Hooker, A. Courville, G. Clark, Y. Dauphin, and A. Frome, "What do compressed deep neural networks forget?" arXiv preprint arXiv: 1911. 05248, 2019.
S. Hooker, N. Moorosi, G. Clark, S. Bengio, and E. Denton, "Characterising bias in compressed models, " arXiv preprint arXiv: 2010. 03058, 2020.
C. Kowalski, A. Famili, and Y. Lao, "Towards model quantization on the resilience against membership inference attacks, " in IEEE International Conference on Image Processing, 2022, pp. 3646-3650.
Y. Jin, W. Lou, and Y. Gao, "Membership inference attacks against compression models, " Computing, vol. 105, no. 11, pp. 2419-2442, 2023.
R. Shokri, M. Stronati, C. Song, and V. Shmatikov, "Membership inference attacks against machine learning models, " in Proceedings of the 2017 IEEE Symposium on Security and Privacy, 2017, pp. 3-18.
S. Yeom, M. Fredrikson, and S. Jha, "Privacy risk in machine learning: Analyzing the connection to overfitting, " Proceedings of the IEEE Computer Security Foundations Symposium, pp. 268-282, 2018.
H. Hu and J. Pang, "Loss and likelihood based membership inference of diffusion models, " in Proceedings of the 26th International Conference on Information Security, 2023, pp. 121-141.
B. Chen, H. Zhang, and X. Liu, "Deep neural network quantization framework for effective defense against membership inference attacks, " Sensors, vol. 23, no. 18, p. 7722, 2023.
N. Carlini, S. Chien, M. Nasr, S. Song, A. Terzis, and F. Tramer, "Membership inference attacks from first principles, " in Proceedings of the 2022 IEEE Symposium on Security and Privacy, 2022, pp. 1897-1914.
M. Nagel, R. A. Amjad, M. Van Baalen, C. Louizos, and T. Blankevoort, "Up or down Adaptive rounding for post-training quantization, " in Proceedings of International Conference on Machine Learning, 2020, pp. 7197-7206.
Y. Li, R. Gong, X. Tan, Y. Yang, P. Hu, Q. Zhang, F. Yu, W. Wang, and S. Gu, "{BRECQ}: Pushing the limit of post-training quantization by block reconstruction, " in Proceedings of International Conference on Learning Representations, 2021.
E. Frantar and D. Alistarh, "Optimal brain compression: A framework for accurate post-training quantization and pruning, " Advances in Neural Information Processing Systems, vol. 35, pp. 4475-4488, 2022.
S. Ma, H. Wang, L. Ma, L. Wang, W. Wang, S. Huang, L. Dong, R. Wang, J. Xue, and F. Wei, "The era of 1-bit llms: All large language models are in 1. 58 bits, " arXiv preprint arXiv: 2402. 17764, 2024.
A. Krizhevsky, "Learning multiple layers of features from tiny images, " University of Toronto, Tech. Rep., 2009.
Y. Le and X. Yang, "Tiny imagenet visual recognition challenge, " CS231N Stanford, vol. 7, no. 7, p. 3, 2015.
C. Zhang, S. Bengio, M. Hardt, B. Recht, and O. Vinyals, "Understanding deep learning requires rethinking generalization, " in Proceedings of the International Conference on Learning Representations, 2017.
M. Abadi, A. Chu, I. Goodfellow, H. B. McMahan, I. Mironov, K. Talwar, and L. Zhang, "Deep learning with differential privacy, " in Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security, 2016, pp. 308-318.
X. Tang, S. Mahloujifar, L. Song, V. Shejwalkar, M. Nasr, A. Houmansadr, and P. Mittal, "Mitigating membership inference attacks by self-distillation through a novel ensemble architecture, " in Proceedings of the 31st USENIX Security Symposium, 2022, pp. 1433-1450.
O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and L. Fei-Fei, "Imagenet large scale visual recognition challenge, " International Journal of Computer Vision, vol. 115, no. 3, pp. 211-252, 2015.
K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition, " in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770-778.
C. Zhang, J. Pang, and S. Mauw, "Spurious privacy leakage in neural networks, " Transactions on Machine Learning Research, 2025.
J. Wang, W. Bao, L. Sun, X. Zhu, B. Cao, and P. S. Yu, "Private model compression via knowledge distillation, " in Proceedings of the AAAI Conference on Artificial Intelligence, 2019, pp. 1190-1197.
J. Chen, K. Sun, and L. Zhao, "Membership inference attacks against compression models, " Computing Journal, 2023.
H. Zhu, R. Wang, Y. Jin, K. Liang, and J. Ning, "Distributed additive encryption and quantization for privacy preserving federated deep learning, " Neurocomputing, vol. 463, pp. 309-327, 2021.
Y. He, M. Zenk, and M. Fritz, "Cossgd: Nonlinear quantization for communication-efficient federated learning, " arXiv preprint arXiv: 2012. 08241, 2020.
N. Lang, E. Sofer, T. Shaked, and N. Shlezinger, "Joint privacy enhancement and quantization in federated learning, " IEEE Transactions on Signal Processing, vol. 71, pp. 295-310, 2023.
C. Zhang, Y. Xie, H. Bai, B. Yu, W. Li, and Y. Gao, "A survey on federated learning, " Knowledge-Based Systems, vol. 216, p. 106775, 2021.
T. Kang, L. Liu, H. He, J. Zhang, S. Song, and K. B. Letaief, "The effect of quantization in federated learning: A rényi differential privacy perspective, " in Proceedings of the 2024 IEEE International Mediterranean Conference on Communications and Networking, 2024, pp. 233-238.
S. Amiri, A. Belloum, S. Klous, and L. Gommans, "Compressive differentially private federated learning through universal vector quantization, " in Proceedings of the AAAI Workshop on Privacy-Preserving Artificial Intelligence, 2021, pp. 2-9.
Z. Deng, V. Ramkumar, R. Bitar, and N. Raviv, "Private inference in quantized models, " IEEE Transactions on Information Theory, 2025.
C.-Y. Yang, G. Ramshankar, N. Eliopoulos, P. Jajal, S. Nambiar, E. Miller, X. Zhang, D. Tian, S.-H. Chen, C.-F. Perng et al., "Securing deep neural networks on edge from membership inference attacks using trusted execution environments, " in Proceedings of the 29th ACM/IEEE International Symposium on Low Power Electronics and Design, 2024, pp. 1-6.
A. Famili and Y. Lao, "Deep neural network quantization framework for effective defense against membership inference attacks, " Sensors, vol. 23, no. 18, p. 7722, 2023.
J. Kaplan, S. McCandlish, T. Henighan, T. B. Brown, B. Chess, R. Child, S. Gray, A. Radford, J. Wu, and D. Amodei, "Scaling laws for neural language models, " arXiv preprint arXiv: 2001. 08361, 2020.