# DP-MGTD: Privacy-Preserving Machine-Generated Text Detection via Adaptive Differentially Private Entity Sanitization

Source: [DP-MGTD: Privacy-Preserving Machine-Generated Text Detection via Adaptive Differentially Private Entity Sanitization](<https://www.sota2.com/research/paper/69608b6553fdd5c361744159>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-07-31T05:00:01.455Z

Authors: Lionel Z. Wang, Yusheng Zhao, Jiabin Luo, Xinfeng Li, Lixu Wang, Yinan Peng, Haoyang Li, XiaoFeng Wang, Wei Dong

Published: 2026-01-08T06:33:15.000Z

## Abstract

The deployment of Machine-Generated Text (MGT) detection systems necessitates processing sensitive user data, creating a fundamental conflict between authorship verification and privacy preservation. Standard anonymization techniques often disrupt linguistic fluency, while rigorous Differential Privacy (DP) mechanisms typically degrade the statistical signals required for accurate detection. To resolve this dilemma, we propose \\textbf{DP-MGTD}, a framework incorporating an Adaptive Differentially Private Entity Sanitization algorithm. Our approach utilizes a two-stage mechanism that performs noisy frequency estimation and dynamically calibrates privacy budgets, applying Laplace and Exponential mechanisms to numerical and textual entities respectively. Crucially, we identify a counter-intuitive phenomenon where the application of DP noise amplifies the distinguishability between human and machine text by exposing distinct sensitivity patterns to perturbation. Extensive experiments on the MGTBench-2.0 dataset show that our method achieves near-perfect detection accuracy, significantly outperforming non-private baselines while satisfying strict privacy guarantees.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Machine-generated text detection on MGTBench 2.0](<https://www.sota2.com/research/sota/machine-generated-text-detection-on-mgtbench-2-0.md>): Machine-generated text detection; MGTBench 2.0; F1 Score (Llama-3.1-70b - ST): 99.7.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2601.04641>)

[PDF](<https://arxiv.org/pdf/2601.04641.pdf>)
