English
Related papers

Related papers: Differentially Private Language Generation and Ide…

200 papers

We demonstrate that it is possible to train large recurrent language models with user-level differential privacy guarantees with only a negligible cost in predictive accuracy. Our work builds on recent advances in the training of deep…

Machine Learning · Computer Science 2018-02-27 H. Brendan McMahan , Daniel Ramage , Kunal Talwar , Li Zhang

Differential privacy allows bounding the influence that training data records have on a machine learning model. To use differential privacy in machine learning, data scientists must choose privacy parameters $(\epsilon,\delta)$. Choosing…

Cryptography and Security · Computer Science 2021-07-21 Daniel Bernau , Günther Eibl , Philip W. Grassal , Hannah Keller , Florian Kerschbaum

The recent successes of large language models (LLMs) have led to a surge of theoretical research into language generation. A recent line of work proposes an abstract view, called language generation in the limit, where generation is seen as…

Combinatorics · Mathematics 2025-04-22 Jon Kleinberg , Fan Wei

We study language generation in the limit under bounded memory. In this task, a learner observes examples from an unknown target language one at a time and must eventually output only new valid examples. Prior work assumes access to the…

Data Structures and Algorithms · Computer Science 2026-05-29 Jon Kleinberg , Anay Mehrotra , Amin Saberi , Grigoris Velegkas

We study language generation in the limit, where an algorithm observes an adversarial enumeration of strings from an unknown target language $K$ and must eventually generate new, unseen strings from $K$. Kleinberg and Mullainathan [KM24]…

Machine Learning · Statistics 2025-11-11 Anay Mehrotra , Grigoris Velegkas , Xifan Yu , Felix Zhou

With the increasing applications of language models, it has become crucial to protect these models from leaking private information. Previous work has attempted to tackle this challenge by training RNN-based language models with…

Computation and Language · Computer Science 2022-07-19 Weiyan Shi , Aiqi Cui , Evan Li , Ruoxi Jia , Zhou Yu

We present new mechanisms for \emph{label differential privacy}, a relaxation of differentially private machine learning that only protects the privacy of the labels in the training set. Our mechanisms cluster the examples in the training…

Machine Learning · Computer Science 2021-10-06 Hossein Esfandiari , Vahab Mirrokni , Umar Syed , Sergei Vassilvitskii

Ensuring user privacy by synthesizing data from large language models (LLMs) tuned under differential privacy (DP) has become popular recently. However, the impact of DP fine-tuned LLMs on the quality of the language and the utility of the…

Computation and Language · Computer Science 2025-09-16 Erion Çano , Ivan Habernal

Differentially private (DP) language model inference is an approach for generating private synthetic text. A sensitive input example is used to prompt an off-the-shelf large language model (LLM) to produce a similar example. Multiple…

Machine Learning · Computer Science 2025-06-06 Kareem Amin , Salman Avestimehr , Sara Babakniya , Alex Bie , Weiwei Kong , Natalia Ponomareva , Umar Syed

Privacy protection with synthetic data generation often uses differentially private statistics and model parameters to quantitatively express theoretical security. However, these methods do not take into account privacy protection due to…

Cryptography and Security · Computer Science 2023-04-03 Takayuki Miura , Toshiki Shibahara , Masanobu Kii , Atsunori Ichikawa , Juko Yamamoto , Koji Chida

Synthetic data has been hailed as the silver bullet for privacy preserving data analysis. If a record is not real, then how could it violate a person's privacy? In addition, deep-learning based generative models are employed successfully to…

Machine Learning · Computer Science 2023-07-14 Benedikt Groß , Gerhard Wunder

We address the challenge of ensuring differential privacy (DP) guarantees in training deep retrieval systems. Training these systems often involves the use of contrastive-style losses, which are typically non-per-example decomposable,…

Computation and Language · Computer Science 2024-05-24 Aldo Gael Carranza , Rezsa Farahani , Natalia Ponomareva , Alex Kurakin , Matthew Jagielski , Milad Nasr

Although current large language models are complex, the most basic specifications of the underlying language generation problem itself are simple to state: given a finite set of training samples from an unknown language, produce valid new…

Data Structures and Algorithms · Computer Science 2024-04-11 Jon Kleinberg , Sendhil Mullainathan

We present an approach for generating differentially private synthetic text using large language models (LLMs), via private prediction. In the private prediction framework, we only require the output synthetic data to satisfy differential…

Machine Learning · Computer Science 2024-10-10 Kareem Amin , Alex Bie , Weiwei Kong , Alexey Kurakin , Natalia Ponomareva , Umar Syed , Andreas Terzis , Sergei Vassilvitskii

Differential privacy (DP) is a class of mathematical standards for assessing the privacy provided by a data-release mechanism. This work concerns two important flavors of DP that are related yet conceptually distinct: pure…

Statistics Theory · Mathematics 2024-08-22 James Bailie , Ruobin Gong

Differential privacy (DP) is a neat privacy definition that can co-exist with certain well-defined data uses in the context of interactive queries. However, DP is neither a silver bullet for all privacy problems nor a replacement for all…

Cryptography and Security · Computer Science 2020-11-05 Josep Domingo-Ferrer , David Sánchez , Alberto Blanco-Justicia

Large language models (LLMs) have presented outstanding performance in code generation and completion. However, fine-tuning these models on private datasets can raise privacy and proprietary concerns, such as the leakage of sensitive…

Cryptography and Security · Computer Science 2026-01-16 Zheng Liu , Chen Gong , Terry Yue Zhuo , Kecen Li , Weichen Yu , Matt Fredrikson , Tianhao Wang

Designing privacy-preserving machine learning algorithms has received great attention in recent years, especially in the setting when the data contains sensitive information. Differential privacy (DP) is a widely used mechanism for data…

Machine Learning · Computer Science 2025-09-11 Chunyang Liao , Deanna Needell , Hayden Schaeffer , Alexander Xue

In the classical identification in the limit model of Gold [1967], a stream of positive examples is presented round by round, and the learner must eventually recover the target hypothesis. Recently, Kleinberg and Mullainathan [2024]…

Machine Learning · Computer Science 2026-05-08 Xiaoyu Li , Andi Han , Jiaojiao Jiang , Junbin Gao

This work considers computationally efficient privacy-preserving data release. We study the task of analyzing a database containing sensitive information about individual participants. Given a set of statistical queries on the data, we want…

Computational Complexity · Computer Science 2011-07-14 Moritz Hardt , Guy N. Rothblum , Rocco A. Servedio