# Cloaked Classifiers: Pseudonymization Strategies on Sensitive Classification Tasks

arXiv: https://arxiv.org/abs/2406.17875 · HTML: https://mlsanity.com/paper/2406.17875/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 57 references that are in the map.
- First posted on arXiv 25 Jun 2024.

## Builds on (most cited first, 15 of 15)

- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [What Does it Mean for a Language Model to Preserve Privacy?](https://mlsanity.com/paper/2202.05520/) (2022)
- [XLM-T: Multilingual Language Models in Twitter for Sentiment Analysis and Beyond](https://mlsanity.com/paper/2104.12250/) (2021)
- [The Text Anonymization Benchmark (TAB): A Dedicated Corpus and Evaluation Framework for Text Anonymization](https://mlsanity.com/paper/2202.00443/) (2022)
- [De-identification of Patient Notes with Recurrent Neural Networks](https://mlsanity.com/paper/1606.03475/) (2016)
- [SOLID: A Large-Scale Semi-Supervised Dataset for Offensive Language Identification](https://mlsanity.com/paper/2004.14454/) (2020)
- [C-sanitized: a privacy model for document redaction and sanitization](https://mlsanity.com/paper/1406.4285/) (2014)
- [Multilingual Auxiliary Tasks Training: Bridging the Gap between Languages for Zero-Shot Transfer of Hate Speech Detection Models](https://mlsanity.com/paper/2210.13029/) (2022)
- [Toward sensitive document release with privacy guarantees](https://mlsanity.com/paper/1701.00436/) (2017)
- [Understanding the Radical Mind: Identifying Signals to Detect Extremist Content on Twitter](https://mlsanity.com/paper/1905.08067/) (2019)
- [Establishing a New State-of-the-Art for French Named Entity Recognition](https://mlsanity.com/paper/2005.13236/) (2020)
- [A survey on extremism analysis using Natural Language Processing](https://mlsanity.com/paper/2104.04069/) (2021)
- [How Much User Context Do We Need? Privacy by Design in Mental Health NLP Application](https://mlsanity.com/paper/2209.02022/) (2022)

## Built on by (most cited first, 3 of 3)

- [Tau-Eval: A Unified Evaluation Framework for Useful and Private Text Anonymization](https://mlsanity.com/paper/2506.05979/) (2025)
- [Beyond Dataset Creation: Critical View of Annotation Variation and Bias Probing of a Dataset for Online Radical Content Detection](https://mlsanity.com/paper/2412.11745/) (2024)
- [IYKYK: Using language models to decode extremist cryptolects](https://mlsanity.com/paper/2506.05635/) (2025)

## Abstract (arXiv)

Protecting privacy is essential when sharing data, particularly in the case of an online radicalization dataset that may contain personal information. In this paper, we explore the balance between preserving data usefulness and ensuring robust privacy safeguards, since regulations like the European GDPR shape how personal information must be handled. We share our method for manually pseudonymizing a multilingual radicalization dataset, ensuring performance comparable to the original data. Furthermore, we highlight the importance of establishing comprehensive guidelines for processing sensitive NLP data by sharing our complete pseudonymization process, our guidelines, the challenges we encountered as well as the resulting dataset.