# Protecting Privacy in Classifiers by Token Manipulation

arXiv: https://arxiv.org/abs/2407.01334 · HTML: https://mlsanity.com/paper/2407.01334/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 31 references that are in the map.
- First posted on arXiv 1 Jul 2024.

## Builds on (most cited first, 16 of 16)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Unified Language Model Pre-training for Natural Language Understanding and Generation](https://mlsanity.com/paper/1905.03197/) (2019)
- [Privacy- and Utility-Preserving Textual Analysis via Calibrated Multivariate Perturbations](https://mlsanity.com/paper/1910.08902/) (2019)
- [Towards Robust and Privacy-preserving Text Representations](https://mlsanity.com/paper/1805.06093/) (2018)
- [Differentially Private Representation for NLP: Formal Guarantee and An Empirical Study on Privacy and Fairness](https://mlsanity.com/paper/2010.01285/) (2020)
- [A Systematic Investigation of Commonsense Knowledge in Large Language Models](https://mlsanity.com/paper/2111.00607/) (2021)
- [Natural Language Understanding with Privacy-Preserving BERT](https://mlsanity.com/paper/2104.07504/) (2021)
- [Privacy-preserving Neural Representations of Text](https://mlsanity.com/paper/1808.09408/) (2018)
- [Local Differential Privacy for Deep Learning](https://mlsanity.com/paper/1908.02997/) (2019)
- [CAPE: Context-Aware Private Embeddings for Private Language Learning](https://mlsanity.com/paper/2108.12318/) (2021)
- [InvBERT: Reconstructing Text from Contextualized Word Embeddings by inverting the BERT pipeline](https://mlsanity.com/paper/2109.10104/) (2021)

## Built on by (most cited first, 1 of 1)

- [Token-Level Privacy in Large Language Models](https://mlsanity.com/paper/2503.03652/) (2025)

## Abstract (arXiv)

Using language models as a remote service entails sending private information to an untrusted provider. In addition, potential eavesdroppers can intercept the messages, thereby exposing the information. In this work, we explore the prospects of avoiding such data exposure at the level of text manipulation. We focus on text classification models, examining various token mapping and contextualized manipulation functions in order to see whether classifier accuracy may be maintained while keeping the original text unrecoverable. We find that although some token mapping functions are easy and straightforward to implement, they heavily influence performance on the downstream task, and via a sophisticated attacker can be reconstructed. In comparison, the contextualized manipulation provides an improvement in performance.