# AnonShield: Scalable On-Premise Pseudonymization for CSIRT Vulnerability Data

arXiv: https://arxiv.org/abs/2606.15650 · HTML: https://mlsanity.com/paper/2606.15650/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 18 references that are in the map.
- First posted on arXiv 5 Apr 2026.

## Builds on (most cited first, 3 of 3)

- [k-Anonymity in Practice: How Generalisation and Suppression Affect Machine Learning Classifiers](https://mlsanity.com/paper/2102.04763/) (2021)
- [AnonLFI 2.0: Extensible Architecture for PII Pseudonymization in CSIRTs with OCR and Technical Recognizers](https://mlsanity.com/paper/2511.15744/) (2025)
- [Structured Extraction of Vulnerabilities in OpenVAS and Tenable WAS Reports Using LLMs](https://mlsanity.com/paper/2511.15745/) (2025)

## Abstract (arXiv)

We present AnonShield, a high-throughput, on-premise pseudonymization system that combines GPU-accelerated NER, streaming processing, caching, and schema-aware configuration. Evaluated on datasets up to 550 MB (70,951 records), AnonShield reduces processing time from over 92 hours to under 10 minutes (up to 738x speedup) while achieving up to 94.2% F1-score and 96.7% recall. Our results show that scalable pseudonymization of vulnerability data is feasible without sacrificing analytical utility, enabling compliant data sharing in operational CSIRT environments.