cs.CLNov 18, 2026

Localizing Text Anonymization for Trustworthy AI: Extending RAT-Bench to Malaysian Microdata and PII

Authors: David Hong Liang Chew, Zexi Yao, Nataša Krčo, Matthieu Meeus, Waqas Khalid Obeidy, Yves-Alexandre de Montjoye

Organizations: Payments Network Malaysia Sdn Bhd (PayNet) · Imperial College London

Abstract

As governments and organizations adopt foundation models for public services and workplace productivity, sensitive citizen, employee, and administrative text may enter LLM workflows through inference, retrieval, fine-tuning, or local model development. We examine whether text anonymizers transfer to new deployment settings by extending RAT-Bench to Malaysia using local microdata, Malaysian PII formats, and culturally grounded transcripts in Malaysian English and Bahasa Malaysia. We evaluate NER- and LLM-based anonymizers using an LLM attacker that infers attributes from anonymized text, measuring both re-identification success and text utility. Across Malaysian English and Bahasa Malaysia, the two LLM anonymizers provide the strongest explicit privacy-utility trade-offs, reducing Easy/Hard re-identification risk to 23-29% while preserving BLEU scores of 0.77-0.94. Non-LLM tools show sharper failure modes, either preserving utility while leaving high residual risk or reducing risk through severe over-redaction, especially in Bahasa Malaysia. These findings suggest that anonymizers should be evaluated against deployment-relevant languages, identifier formats, and cultural contexts before being relied on in public-sector, workplace, or local AI pipelines.

Figures & tables

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Anonymous-by-Construction: An LLM-Driven Framework for Privacy-Preserving Text

    Mar 17, 2026Federico Albanese, Pablo Ronco, Nicolás D'IppolitoPrivacy-Preserving MLPrivacy-Preserving Language Models

  2. LLM Anonymization Against Agentic Re-Identification

    May 29, 2026Ziwen Li, Jianing Wen, Tianshi LiPrivacy-Preserving Language ModelsPrivacy-Utility Tradeoff

  3. Subject-level Inference for Realistic Text Anonymization Evaluation

    Apr 23, 2026Myeong Seok Oh, Dong-Yun Kim, Hanseok Oh +6Privacy Auditing