EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Autoencoder-Enhanced Hierarchical Mondrian Anonymization via Latent Representations

Junpeng Hu, Tao Hu, Zhenwu Xu, Jinan Shen, Minghui Zheng

Entropy · 25.03.2026 · 28 (4) · 372

DOI: 10.3390/e28040372 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Entropy, online erschienen am 25.03.2026. Verfasst von Junpeng Hu und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Cyber Science and Engineering, Sichuan University, Chengdu 610207, China. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China https://ror.org/01h0zpd94.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Releasing structured microdata requires balancing utility and privacy under group-based disclosure risks. We propose AE-LRHMA, a hybrid anonymization framework that performs Mondrian-style hierarchical partitioning in an autoencoder-learned latent space and integrates local (k,e)-microaggregation. To explicitly control sensitive-value concentration and diversity within each equivalence class, we introduce a tunable constraint set consisting of k, a maximum sensitive proportion threshold, and an optional sensitive-entropy threshold (used as a hard gate when enabled and otherwise as a soft term in split scoring). The anonymized output is generated via standard interval/set generalization in the original space. Experiments on Adult and Bank Marketing demonstrate that AE-LRHMA yields lower information loss and more stable group structures than representative baselines under comparable settings. We further report linkage-attack-oriented risk metrics to empirically characterize relative disclosure trends without claiming formal guarantees, such as differential privacy.

Schlagwörter

Stichwörter der Autor:innen

autoencoderdata anonymizationk-anonymitylatent space partitioninglinkage-attack riskmicroaggregation

Autor:innen und Institutionen

  • School of Cyber Science and Engineering, Sichuan University, Chengdu 610207, China.
  • College of Intelligent Science and Engineering, Hubei University for Nationalities, Enshi 445000, China.

Förderung

  • National Natural Science Foundation of China https://ror.org/01h0zpd94

Zitieren

APA

Hu, J., Hu, T., Xu, Z., Shen, J., & Zheng, M. (2026). Autoencoder-Enhanced Hierarchical Mondrian Anonymization via Latent Representations. Entropy, 28(4), 372. https://doi.org/10.3390/e28040372

Vancouver

Hu J, Hu T, Xu Z, Shen J, Zheng M. Autoencoder-Enhanced Hierarchical Mondrian Anonymization via Latent Representations. Entropy. 2026;28(4):372. doi:10.3390/e28040372

BibTeX
@article{Hu2026,
  author = {Hu, Junpeng and Hu, Tao and Xu, Zhenwu and Shen, Jinan and Zheng, Minghui},
  title = {Autoencoder-Enhanced Hierarchical Mondrian Anonymization via Latent Representations},
  journal = {Entropy},
  year = {2026},
  volume = {28},
  number = {4},
  pages = {372},
  doi = {10.3390/e28040372}
}
Kostenlos starten →