Cover Image

Harnessing large-language models to generate private synthetic text

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kurakin, Alexey, Ponomareva, Natalia, Syed, Umar, MacDermed, Liam, Terzis, Andreas
Format:	Preprint
Published:	2023
Subjects:	Machine Learning Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Private prediction for large-scale synthetic text generation
by: Amin, Kareem, et al.
Published: (2024)

Certified Robustness to Clean-Label Poisoning Using Diffusion Denoising
by: Hong, Sanghyun, et al.
Published: (2024)

How to DP-fy Your Data: A Practical Guide to Generating Synthetic Data With Differential Privacy
by: Ponomareva, Natalia, et al.
Published: (2025)

Clustering and Median Aggregation Improve Differentially Private Inference
by: Amin, Kareem, et al.
Published: (2025)

Training generative models from privatized data
by: Reshetova, Daria, et al.
Published: (2023)

Can large language models be privacy preserving and fair medical coders?
by: Dadsetan, Ali, et al.
Published: (2024)

Almost linear time differentially private release of synthetic graphs
by: Liu, Jingcheng, et al.
Published: (2024)

Leveraging large language models for SQL behavior-based database intrusion detection
by: Shlezinger, Meital, et al.
Published: (2025)

Poisoning Web-Scale Training Datasets is Practical
by: Carlini, Nicholas, et al.
Published: (2023)

Near-Optimal differentially private low-rank trace regression with guaranteed private initialization
by: Zha, Mengyue
Published: (2024)

Differentially private Bayesian tests
by: Chakraborty, Abhisek, et al.
Published: (2024)

Evaluating the Robustness of a Production Malware Detection System to Transferable Adversarial Attacks
by: Nasr, Milad, et al.
Published: (2025)

Exploring the limits of strong membership inference attacks on large language models
by: Hayes, Jamie, et al.
Published: (2025)

Towards the generation of hierarchical attack models from cybersecurity vulnerabilities using language models
by: Sowka, Kacper, et al.
Published: (2024)

The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD
by: Steinke, Thomas, et al.
Published: (2024)

Learning diverse attacks on large language models for robust red-teaming and safety tuning
by: Lee, Seanie, et al.
Published: (2024)

Methods for generating and evaluating synthetic longitudinal patient data: a systematic review
by: Perkonoja, Katariina, et al.
Published: (2023)

Excuse me, sir? Your language model is leaking (information)
by: Zamir, Or
Published: (2024)

Accurate, private, secure, federated U-statistics with higher degree
by: Sinh, Quentin, et al.
Published: (2026)

Resampling methods for private statistical inference
by: Chadha, Karan, et al.
Published: (2024)

The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections
by: Nasr, Milad, et al.
Published: (2025)

Robust image classification with multi-modal large language models
by: Villani, Francesco, et al.
Published: (2024)

Lessons from Defending Gemini Against Indirect Prompt Injections
by: Shi, Chongyang, et al.
Published: (2025)

Towards Harnessing the Power of LLMs for ABAC Policy Mining
by: Babasaheb, More Aayush, et al.
Published: (2025)

Modulated learning for private and distributed regression with just a single sample per client device
by: Vepakomma, Praneeth, et al.
Published: (2026)

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

PURL: Safe and Effective Sanitization of Link Decoration
by: Munir, Shaoor, et al.
Published: (2023)

SSCAE -- Semantic, Syntactic, and Context-aware natural language Adversarial Examples generator
by: Asl, Javad Rafiei, et al.
Published: (2024)

Attack and defense techniques in large language models: A survey and new perspectives
by: Liao, Zhiyu, et al.
Published: (2025)

Advancing TTP Analysis: Harnessing the Power of Large Language Models with Retrieval Augmented Generation
by: Fayyazi, Reza, et al.
Published: (2023)

Harnessing PU Learning for Enhanced Cloud-based DDoS Detection: A Comparative Analysis
by: Dilworth, Robert, et al.
Published: (2024)

Privacy-hardened and hallucination-resistant synthetic data generation with logic-solvers
by: Burgess, Mark A., et al.
Published: (2024)

Data value estimation on private gradients
by: Zhou, Zijian, et al.
Published: (2024)

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

Differentially private and decentralized randomized power method
by: Nicolas, Julien, et al.
Published: (2024)

Can a large language model be a gaslighter?
by: Li, Wei, et al.
Published: (2024)

"You still have to study" -- On the Security of LLM generated code
by: Goetz, Stefan, et al.
Published: (2024)

The importance of feature preprocessing for differentially private linear optimization
by: Sun, Ziteng, et al.
Published: (2023)

Hiding Backdoors within Event Sequence Data via Poisoning Attacks
by: Ermilova, Alina, et al.
Published: (2023)

Towards Sustainable SecureML: Quantifying Carbon Footprint of Adversarial Machine Learning
by: Hasan, Syed Mhamudul, et al.
Published: (2024)