# The Double-edged Sword of LLM-based Data Reconstruction: Understanding and Mitigating Contextual Vulnerability in Word-level Differential Privacy Text Sanitization

arXiv: https://arxiv.org/abs/2508.18976 · HTML: https://mlsanity.com/paper/2508.18976/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 45 references that are in the map.
- First posted on arXiv 26 Aug 2025.

## Builds on (most cited first, 26 of 26)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs](https://mlsanity.com/paper/2402.03927/) (2024)
- [Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising](https://mlsanity.com/paper/1805.06530/) (2018)
- [What Does it Mean for a Language Model to Preserve Privacy?](https://mlsanity.com/paper/2202.05520/) (2022)
- [Privacy- and Utility-Preserving Textual Analysis via Calibrated Multivariate Perturbations](https://mlsanity.com/paper/1910.08902/) (2019)
- [Differential Privacy for Text Analytics via Natural Text Sanitization](https://mlsanity.com/paper/2106.01221/) (2021)
- [The Limits of Word Level Differential Privacy](https://mlsanity.com/paper/2205.02130/) (2022)
- [Locally Differentially Private Document Generation Using Zero Shot Prompting](https://mlsanity.com/paper/2310.16111/) (2023)
- [Generalised Differential Privacy for Text Document Processing](https://mlsanity.com/paper/1811.10256/) (2018)
- [A Customized Text Sanitization Mechanism with Differential Privacy](https://mlsanity.com/paper/2207.01193/) (2022)
- [Leveraging Hierarchical Representations for Preserving Privacy and Utility in Text](https://mlsanity.com/paper/1910.08917/) (2019)
- [TEM: High Utility Metric Differential Privacy on Text](https://mlsanity.com/paper/2107.07928/) (2021)
- [A Differentially Private Text Perturbation Method Using a Regularized Mahalanobis Metric](https://mlsanity.com/paper/2010.11947/) (2020)
- [DP-BART for Privatized Text Rewriting under Local Differential Privacy](https://mlsanity.com/paper/2302.07636/) (2023)
- [The Impact of the U.S. Census Disclosure Avoidance System on Redistricting and Voting Rights Analysis](https://mlsanity.com/paper/2105.14197/) (2021)
- [Guiding Text-to-Text Privatization by Syntax](https://mlsanity.com/paper/2306.01471/) (2023)
- [Driving Context into Text-to-Text Privatization](https://mlsanity.com/paper/2306.01457/) (2023)
- [Differential Privacy in Natural Language Processing: The Story So Far](https://mlsanity.com/paper/2208.08140/) (2022)
- [1-Diffractor: Efficient and Utility-Preserving Text Obfuscation Leveraging Word-Level Metric Differential Privacy](https://mlsanity.com/paper/2405.01678/) (2024)
- [Just Rewrite It Again: A Post-Processing Method for Enhanced Semantic Similarity and Privacy Preservation of Differentially Private Rewritten Text](https://mlsanity.com/paper/2405.19831/) (2024)
- [On the Vulnerability of Text Sanitization](https://mlsanity.com/paper/2410.17052/) (2024)
- [On the Impact of Noise in Differentially Private Text Rewriting](https://mlsanity.com/paper/2501.19022/) (2025)
- [Research Challenges in Designing Differentially Private Text Generation Mechanisms](https://mlsanity.com/paper/2012.05403/) (2020)
- [Spend Your Budget Wisely: Towards an Intelligent Distribution of the Privacy Budget in Differentially Private Text Rewriting](https://mlsanity.com/paper/2503.22379/) (2025)

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

- [PrivBench: A Holistic and Modular Benchmarking Platform for Evaluating Text-to-Text Privatization](https://mlsanity.com/paper/2608.29624/) (2026)

## Abstract (arXiv)

Differentially private text sanitization refers to the process of privatizing texts under the framework of Differential Privacy (DP), providing provable privacy guarantees while also empirically defending against adversaries seeking to harm privacy. Despite their simplicity, DP text sanitization methods operating at the word level exhibit a number of shortcomings, among them the tendency to leave contextual clues from the original texts due to randomization during sanitization unicodex2013 this we refer to as textitcontextual vulnerability. Given the powerful contextual understanding and inference capabilities of Large Language Models (LLMs), we explore to what extent LLMs can be leveraged to exploit the contextual vulnerability of DP-sanitized texts. We expand on previous work not only in the use of advanced LLMs, but also in testing a broader range of sanitization mechanisms at various privacy levels. Our experiments uncover a double-edged sword effect of LLM-based data reconstruction attacks on privacy and utility: while LLMs can indeed infer original semantics and sometimes degrade empirical privacy protections, they can also be used for good, to improve the quality and privacy of DP-sanitized texts. Based on our findings, we propose recommendations for using LLM data reconstruction as a post-processing step, serving to increase privacy protection by thinking adversarially.