# A Customized Text Sanitization Mechanism with Differential Privacy

arXiv: https://arxiv.org/abs/2207.01193 · HTML: https://mlsanity.com/paper/2207.01193/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 36 references that are in the map.
- First posted on arXiv 4 Jul 2022.

## Builds on (most cited first, 20 of 20)

- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Publicly Available Clinical BERT Embeddings](https://mlsanity.com/paper/1904.03323/) (2019)
- [The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks](https://mlsanity.com/paper/1802.08232/) (2018)
- [Large Language Models Can Be Strong Differentially Private Learners](https://mlsanity.com/paper/2110.05679/) (2021)
- [Information Leakage in Embedding Models](https://mlsanity.com/paper/2004.00053/) (2020)
- [Counter-fitting Word Vectors to Linguistic Constraints](https://mlsanity.com/paper/1603.00892/) (2016)
- [Privacy- and Utility-Preserving Textual Analysis via Calibrated Multivariate Perturbations](https://mlsanity.com/paper/1910.08902/) (2019)
- [Large-Scale Differentially Private BERT](https://mlsanity.com/paper/2108.01624/) (2021)
- [Differential Privacy for Text Analytics via Natural Text Sanitization](https://mlsanity.com/paper/2106.01221/) (2021)
- [Differentially Private Representation for NLP: Formal Guarantee and An Empirical Study on Privacy and Fairness](https://mlsanity.com/paper/2010.01285/) (2020)
- [Natural Language Understanding with Privacy-Preserving BERT](https://mlsanity.com/paper/2104.07504/) (2021)
- [Leveraging Hierarchical Representations for Preserving Privacy and Utility in Text](https://mlsanity.com/paper/1910.08917/) (2019)
- [Survey: Leakage and Privacy at Inference Time](https://mlsanity.com/paper/2107.01614/) (2021)
- [MedSTS: A Resource for Clinical Semantic Textual Similarity](https://mlsanity.com/paper/1808.09397/) (2018)
- [Privacy Regularization: Joint Privacy-Utility Optimization in Language Models](https://mlsanity.com/paper/2103.07567/) (2021)
- [An Efficient DP-SGD Mechanism for Large Scale NLP Models](https://mlsanity.com/paper/2107.14586/) (2021)
- [Utility-Optimized Local Differential Privacy Mechanisms for Distribution Estimation](https://mlsanity.com/paper/1807.11317/) (2018)

## Built on by (most cited first, 30 of 52)

- [Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation](https://mlsanity.com/paper/2309.11765/) (2023)
- [Locally Differentially Private Document Generation Using Zero Shot Prompting](https://mlsanity.com/paper/2310.16111/) (2023)
- [CoGenesis: A Framework Collaborating Large and Small Language Models for Secure Context-Aware Instruction Following](https://mlsanity.com/paper/2403.03129/) (2024)
- [Privacy Preserving Prompt Engineering: A Survey](https://mlsanity.com/paper/2404.06001/) (2024)
- [DP-MLM: Differentially Private Text Rewriting Using Masked Language Models](https://mlsanity.com/paper/2407.00637/) (2024)
- [A Survey of Conversational Search](https://mlsanity.com/paper/2410.15576/) (2024)
- [Differentially Private Natural Language Models: Recent Advances and Future Directions](https://mlsanity.com/paper/2301.09112/) (2023)
- [Evaluating Differentially Private Synthetic Data Generation in High-Stakes Domains](https://mlsanity.com/paper/2410.08327/) (2024)
- [Data-adaptive Differentially Private Prompt Synthesis for In-Context Learning](https://mlsanity.com/paper/2410.12085/) (2024)
- [On the Impact of Noise in Differentially Private Text Rewriting](https://mlsanity.com/paper/2501.19022/) (2025)
- [SynthTextEval: Synthetic Text Data Generation and Evaluation for High-Stakes Domains](https://mlsanity.com/paper/2507.07229/) (2025)
- [DP-Fusion: Token-Level Differentially Private Inference for Large Language Models](https://mlsanity.com/paper/2507.04531/) (2025)
- [Differentially Private Synthetic Text Generation for Retrieval-Augmented Generation (RAG)](https://mlsanity.com/paper/2510.06719/) (2025)
- [Spend Your Budget Wisely: Towards an Intelligent Distribution of the Privacy Budget in Differentially Private Text Rewriting](https://mlsanity.com/paper/2503.22379/) (2025)
- [VFLAIR-LLM: A Comprehensive Framework and Benchmark for Split Learning of LLMs](https://mlsanity.com/paper/2508.03097/) (2025)
- [How do we measure privacy in text? A survey of text anonymization metrics](https://mlsanity.com/paper/2512.01109/) (2025)
- [Towards Harnessing the Collaborative Power of Large and Small Models for Domain Tasks](https://mlsanity.com/paper/2504.17421/) (2025)
- [A Collocation-based Method for Addressing Challenges in Word-level Metric Differential Privacy](https://mlsanity.com/paper/2407.00638/) (2024)
- [Improving Privacy Benefits of Redaction](https://mlsanity.com/paper/2501.17762/) (2025)
- [DP-GTR: Differentially Private Prompt Protection via Group Text Rewriting](https://mlsanity.com/paper/2503.04990/) (2025)
- [Inspecting the Representation Manifold of Differentially-Private Text](https://mlsanity.com/paper/2503.14991/) (2025)
- [Differentially Private and Communication Efficient Large Language Model Split Inference via Stochastic Quantization and Soft Prompt](https://mlsanity.com/paper/2602.11513/) (2026)
- [Mitigating Gradient Inversion Risks in Language Models via Token Obfuscation](https://mlsanity.com/paper/2602.15897/) (2026)
- [Towards Privacy-Preserving LLM Inference via Covariant Obfuscation (Technical Report)](https://mlsanity.com/paper/2603.01499/) (2026)
- [STAMP: Selective Task-Aware Mechanism for Text Privacy](https://mlsanity.com/paper/2603.12237/) (2026)
- [From Prompts to Responses: Dual-Sided Data Leakage and Defense in Split Large Language Models](https://mlsanity.com/paper/2606.14210/) (2026)
- [Investigating User Perspectives on Differentially Private Text Privatization](https://mlsanity.com/paper/2503.09338/) (2025)
- [The Double-edged Sword of LLM-based Data Reconstruction: Understanding and Mitigating Contextual Vulnerability in Word-level Differential Privacy Text Sanitization](https://mlsanity.com/paper/2508.18976/) (2025)
- [Towards Confidential and Efficient LLM Inference with Dual Privacy Protection](https://mlsanity.com/paper/2509.09091/) (2025)
- [OSNIP: Breaking the Privacy-Utility-Efficiency Trilemma in LLM Inference via Obfuscated Semantic Null Space](https://mlsanity.com/paper/2601.22752/) (2026)

## Abstract (arXiv)

As privacy issues are receiving increasing attention within the Natural Language Processing (NLP) community, numerous methods have been proposed to sanitize texts subject to differential privacy. However, the state-of-the-art text sanitization mechanisms based on metric local differential privacy (MLDP) do not apply to non-metric semantic similarity measures and cannot achieve good trade-offs between privacy and utility. To address the above limitations, we propose a novel Customized Text (CusText) sanitization mechanism based on the original ε-differential privacy (DP) definition, which is compatible with any similarity measure. Furthermore, CusText assigns each input token a customized output set of tokens to provide more advanced privacy protection at the token level. Extensive experiments on several benchmark datasets show that CusText achieves a better trade-off between privacy and utility than existing mechanisms. The code is available at https://github.com/sai4july/CusText.