Cover Image

Spend Your Budget Wisely: Towards an Intelligent Distribution of the Privacy Budget in Differentially Private Text Rewriting

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Meisenbacher, Stephen, Lee, Chaeeun Joy, Matthes, Florian
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

The Double-edged Sword of LLM-based Data Reconstruction: Understanding and Mitigating Contextual Vulnerability in Word-level Differential Privacy Text Sanitization
by: Meisenbacher, Stephen, et al.
Published: (2025)

With Privacy, Size Matters: On the Importance of Dataset Size in Differentially Private Text Rewriting
by: Meisenbacher, Stephen, et al.
Published: (2025)

A Systematic Exploration of Text Decomposition and Budget Distribution in Differentially Private Text Obfuscation
by: Meisenbacher, Stephen, et al.
Published: (2026)

SoK: Privacy Risks and Mitigations in Retrieval-Augmented Generation Systems
by: Bodea, Andreea-Elena, et al.
Published: (2026)

A Case Study on the Impact of Anonymization Along the RAG Pipeline
by: Bodea, Andreea-Elena, et al.
Published: (2026)

Just Rewrite It Again: A Post-Processing Method for Enhanced Semantic Similarity and Privacy Preservation of Differentially Private Rewritten Text
by: Meisenbacher, Stephen, et al.
Published: (2024)

On the Impact of Noise in Differentially Private Text Rewriting
by: Meisenbacher, Stephen, et al.
Published: (2025)

DP-BART for Privatized Text Rewriting under Local Differential Privacy
by: Igamberdiev, Timour, et al.
Published: (2023)

Thinking Outside of the Differential Privacy Box: A Case Study in Text Privatization with Language Model Prompting
by: Meisenbacher, Stephen, et al.
Published: (2024)

DP-MLM: Differentially Private Text Rewriting Using Masked Language Models
by: Meisenbacher, Stephen, et al.
Published: (2024)

Beyond Theoretical Bounds: Empirical Privacy Loss Calibration for Text Rewriting Under Local Differential Privacy
by: Li, Weijun, et al.
Published: (2026)

Leveraging Semantic Triples for Private Document Generation with Local Differential Privacy Guarantees
by: Meisenbacher, Stephen, et al.
Published: (2025)

Investigating User Perspectives on Differentially Private Text Privatization
by: Meisenbacher, Stephen, et al.
Published: (2025)

1-Diffractor: Efficient and Utility-Preserving Text Obfuscation Leveraging Word-Level Metric Differential Privacy
by: Meisenbacher, Stephen, et al.
Published: (2024)

Limits of Personalizing Differential Privacy Budgets
by: Cyffers, Edwige, et al.
Published: (2026)

DP-MGTD: Privacy-Preserving Machine-Generated Text Detection via Adaptive Differentially Private Entity Sanitization
by: Wang, Lionel Z., et al.
Published: (2026)

Elephants Do Not Forget: Differential Privacy with State Continuity for Privacy Budget
by: Jin, Jiankai, et al.
Published: (2024)

Adaptive Privacy Budgeting
by: Liang, Yuting, et al.
Published: (2026)

Differentially Private Federated Learning With Time-Adaptive Privacy Spending
by: Kiani, Shahrzad, et al.
Published: (2025)

Differentially Private Knowledge Distillation via Synthetic Text Generation
by: Flemings, James, et al.
Published: (2024)

How Private is Your Attention? Bridging Privacy with In-Context Learning
by: Bonnerjee, Soham, et al.
Published: (2025)

Budget Recycling Differential Privacy
by: Jiang, Bo, et al.
Published: (2024)

Secret-Protected Evolution for Differentially Private Synthetic Text Generation
by: Wang, Tianze, et al.
Published: (2025)

A Collocation-based Method for Addressing Challenges in Word-level Metric Differential Privacy
by: Meisenbacher, Stephen, et al.
Published: (2024)

Cookie Monster: Efficient On-device Budgeting for Differentially-Private Ad-Measurement Systems
by: Tholoniat, Pierre, et al.
Published: (2024)

Differentially Private Synthetic Text Generation for Retrieval-Augmented Generation (RAG)
by: Mori, Junki, et al.
Published: (2025)

ContinuousBench: Can Differentially Private Synthetic Text Improve Capabilities?
by: Liu, Peihan, et al.
Published: (2026)

Prior-itizing Privacy: A Bayesian Approach to Setting the Privacy Budget in Differential Privacy
by: Kazan, Zeki, et al.
Published: (2023)

LLM-based Privacy Data Augmentation Guided by Knowledge Distillation with a Distribution Tutor for Medical Text Classification
by: Song, Yiping, et al.
Published: (2024)

Synthetic Query Generation for Privacy-Preserving Deep Retrieval Systems using Differentially Private Language Models
by: Carranza, Aldo Gael, et al.
Published: (2023)

TrojanStego: Your Language Model Can Secretly Be A Steganographic Privacy Leaking Agent
by: Meier, Dominik, et al.
Published: (2025)

InvisibleInk: High-Utility and Low-Cost Text Generation with Differential Privacy
by: Vinod, Vishnu, et al.
Published: (2025)

Randomized Response with Gradual Release of Privacy Budget
by: Pan, Mingen
Published: (2024)

Differentially Private Retrieval-Augmented Generation
by: Tang, Tingting, et al.
Published: (2026)

CRSet: Private Non-Interactive Verifiable Credential Revocation
by: Hoops, Felix, et al.
Published: (2025)

A Comparative Analysis of Word-Level Metric Differential Privacy: Benchmarking The Privacy-Utility Trade-off
by: Meisenbacher, Stephen, et al.
Published: (2024)

Optimal Allocation of Privacy Budget on Hierarchical Data Release
by: Ko, Joonhyuk, et al.
Published: (2025)

Beyond Text: Unveiling Privacy Vulnerabilities in Multi-modal Retrieval-Augmented Generation
by: Zhang, Jiankun, et al.
Published: (2025)

MaskSQL: Safeguarding Privacy for LLM-Based Text-to-SQL via Abstraction
by: Abedini, Sepideh, et al.
Published: (2025)

Privacy-Preserving Retrieval-Augmented Generation with Differential Privacy
by: Koga, Tatsuki, et al.
Published: (2024)