Defense Against Membership Inference Attacks via Normalizing Flow-Based Adversarial Sample
IEEE Transactions on Services Computing · 2026-07 · 19 (4) · 2776-2787
DOI: 10.1109/tsc.2026.3697251 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Services Computing, 2026-07. Verfasst von Guangxu Xie und 3 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
An attacker can determine if a specific input belongs to a deep learning model’s training set by analyzing the complete confidence vector output, known as a membership inference attack. To counter this type of attack, a common defense strategy is to add adversarial noise to the confidence vector to enhance the model’s resilience. However, existing research indicates that defenses against adversarial examples may introduce new security risks to membership inference defenses via adversarial examples. Against this backdrop, this paper proposes a more robust adversarial example defense strategy. By generating adversarial examples with distributions similar to normal samples, we can reduce the impact of distributional differences on the defense model’s security. Leveraging normalizing flow, adding noise to the hidden layer of a flow model trained on normal samples generates adversarial examples that resemble normal ones, enhancing defense robustness. Additionally, limiting the information accessible to the attack model further strengthens robustness. To accelerate convergence, a bidirectional mean update method is employed. The proposed strategy demonstrates effectiveness not only in defending against membership inference attacks but also in mitigating attribute inference attacks. Finally, experiments on real-world datasets validate the effectiveness of the proposed strategy.
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
- Fundamental Research Funds for the Central Universities
- Shaanxi Natural Science Basic Research Project
Zitieren
APA
Xie, G., Xiao, Y., Pei, Q., & Huang, H. (2026). Defense Against Membership Inference Attacks via Normalizing Flow-Based Adversarial Sample. IEEE Transactions on Services Computing, 19(4), 2776-2787. https://doi.org/10.1109/tsc.2026.3697251
Vancouver
Xie G, Xiao Y, Pei Q, Huang H. Defense Against Membership Inference Attacks via Normalizing Flow-Based Adversarial Sample. IEEE Transactions on Services Computing. 2026;19(4):2776-2787. doi:10.1109/tsc.2026.3697251
BibTeX
@article{Xie2026,
author = {Xie, Guangxu and Xiao, Yang and Pei, Qingqi and Huang, Haibo},
title = {Defense Against Membership Inference Attacks via Normalizing Flow-Based Adversarial Sample},
journal = {IEEE Transactions on Services Computing},
year = {2026},
volume = {19},
number = {4},
pages = {2776--2787},
doi = {10.1109/tsc.2026.3697251}
}
EUVIMED