English
Related papers

Related papers: DP-MGTD: Privacy-Preserving Machine-Generated Text…

200 papers

Training generative machine learning models to produce synthetic tabular data has become a popular approach for enhancing privacy in data sharing. As this typically involves processing sensitive personal information, releasing either the…

Cryptography and Security · Computer Science 2026-02-02 Georgi Ganev , Emiliano De Cristofaro

Developing machine learning methods that are privacy preserving is today a central topic of research, with huge practical impacts. Among the numerous ways to address privacy-preserving learning, we here take the perspective of computing the…

Machine Learning · Computer Science 2021-07-06 Alain Rakotomamonjy , Liva Ralaivola

Applying machine learning (ML) to sensitive domains requires privacy protection of the underlying training data through formal privacy frameworks, such as differential privacy (DP). Yet, usually, the privacy of the training data comes at…

Machine Learning · Computer Science 2022-11-09 Franziska Boenisch , Christopher Mühl , Roy Rinberg , Jannis Ihrig , Adam Dziedzic

Language models are widely deployed to provide automatic text completion services in user products. However, recent research has revealed that language models (especially large ones) bear considerable risk of memorizing private training…

Computation and Language · Computer Science 2022-12-19 C. M. Downey , Wei Dai , Huseyin A. Inan , Kim Laine , Saurabh Naik , Tomasz Religa

The goal of differentially private text obfuscation is to obfuscate, or "perturb", input texts with Differential Privacy (DP) guarantees, such that the private output texts are quantifiably indistinguishable from the originals. While…

Computation and Language · Computer Science 2026-05-05 Stephen Meisenbacher , Angelo Kleinert , Florian Matthes

In today's digital world, casual user-generated content often contains subtle cues that may inadvertently expose sensitive personal attributes. Such risks underscore the growing importance of effective text anonymization to safeguard…

Computation and Language · Computer Science 2025-07-01 Chenyang Shao , Tianxing Li , Chenhao Pu , Fengli Xu , Yong Li

Retrieval-Augmented Generation (RAG) enhances the factual accuracy of large language models (LLMs) by conditioning outputs on external knowledge sources. However, when retrieval involves private or sensitive data, RAG systems are…

Computation and Language · Computer Science 2025-08-06 Haoran Wang , Xiongxiao Xu , Baixiang Huang , Kai Shu

Synthetic data has the potential to improve the performance, training efficiency, and privacy of real training examples. Nevertheless, existing approaches for synthetic text generation are mostly heuristics and cannot generate…

Machine Learning · Computer Science 2025-06-10 Dang Nguyen , Zeman Li , Mohammadhossein Bateni , Vahab Mirrokni , Meisam Razaviyayn , Baharan Mirzasoleiman

In this paper, we introduce a novel concept of user-entity differential privacy (UeDP) to provide formal privacy protection simultaneously to both sensitive entities in textual data and data owners in learning natural language models…

Cryptography and Security · Computer Science 2022-11-10 Phung Lai , NhatHai Phan , Tong Sun , Rajiv Jain , Franck Dernoncourt , Jiuxiang Gu , Nikolaos Barmpalios

Machine-generated texts (MGTs) pose risks such as disinformation and phishing, underscoring the need for reliable detection. Metric-based methods, which extract statistically distinguishable features of MGTs, are often more practical than…

Computation and Language · Computer Science 2026-05-18 Chenwang Wu , Yiuming Cheung , Bo Han , Shuhai Zhang , Defu Lian

Language models are capable of memorizing detailed patterns and information, leading to a double-edged effect: they achieve impressive modeling performance on downstream tasks with the stored knowledge but also raise significant privacy…

Artificial Intelligence · Computer Science 2024-10-07 Xianzhi Li , Ran Zmigrod , Zhiqiang Ma , Xiaomo Liu , Xiaodan Zhu

Nowadays, differential privacy (DP) has become a well-accepted standard for privacy protection, and deep neural networks (DNN) have been immensely successful in machine learning. The combination of these two techniques, i.e., deep learning…

Cryptography and Security · Computer Science 2024-08-02 Jianxin Wei , Ergute Bao , Xiaokui Xiao , Yin Yang

Maximum mean discrepancy (MMD) is a particularly useful distance metric for differentially private data generation: when used with finite-dimensional features it allows us to summarize and privatize the data distribution once, which we can…

Machine Learning · Computer Science 2024-02-29 Yilin Yang , Kamil Adamczewski , Danica J. Sutherland , Xiaoxiao Li , Mijung Park

We propose a method for the release of differentially private synthetic datasets. In many contexts, data contain sensitive values which cannot be released in their original form in order to protect individuals' privacy. Synthetic data is a…

Methodology · Statistics 2018-05-25 Joshua Snoke , Aleksandra Slavković

Several companies (e.g., Meta, Google) have initiated "data-for-good" projects where aggregate location data are first sanitized and released publicly, which is useful to many applications in transportation, public health (e.g., COVID-19…

Databases · Computer Science 2022-08-23 Ritesh Ahuja , Sepanta Zeighami , Gabriel Ghinita , Cyrus Shahabi

The study of Differential Privacy (DP) in Natural Language Processing often views the task of text privatization as a $\textit{rewriting}$ task, in which sensitive input texts are rewritten to hide explicit or implicit private information.…

Computation and Language · Computer Science 2024-06-03 Stephen Meisenbacher , Florian Matthes

The rapid advancement of Large Language Models (LLMs) has ushered in an era where AI-generated text is increasingly indistinguishable from human-generated content. Detecting AI-generated text has become imperative to combat misinformation,…

Computation and Language · Computer Science 2024-06-12 Ye Zhang , Qian Leng , Mengran Zhu , Rui Ding , Yue Wu , Jintong Song , Yulu Gong

Achieving differential privacy (DP) guarantees in fully decentralized machine learning is challenging due to the absence of a central aggregator and varying trust assumptions among nodes. We present a framework for DP analysis of…

Machine Learning · Computer Science 2026-02-06 Antti Koskela , Tejas Kulkarni

Data privacy is important in the AI era, and differential privacy (DP) is one of the golden solutions. However, DP is typically applicable only if data have a bounded underlying distribution. We address this limitation by leveraging…

Cryptography and Security · Computer Science 2026-02-27 Zilong Cao , Xuan Bi , Hai Zhang

Current practices for reporting the level of differential privacy (DP) protection for machine learning (ML) algorithms such as DP-SGD provide an incomplete and potentially misleading picture of the privacy guarantees. For instance, if only…

Machine Learning · Computer Science 2025-10-03 Juan Felipe Gomez , Bogdan Kulynych , Georgios Kaissis , Flavio P. Calmon , Jamie Hayes , Borja Balle , Antti Honkela