相关论文: ACTG-ARL: Differentially Private Conditional Text …

Differentially private (DP) synthetic data generation is a promising technique for utilizing private datasets that otherwise cannot be exposed for model training or other analytics. While much research literature has focused on generating…

Large language models benefit from training with a large amount of unlabeled text, which gives them increasingly fluent and diverse generation capabilities. However, using these models for text generation that takes into account target…

Paraphrase generation plays an essential role in natural language process (NLP), and it has many downstream applications. However, training supervised paraphrase models requires many annotated paraphrase pairs, which are usually costly to…

Randomized controlled trials (RCTs) have become powerful tools for assessing the impact of interventions and policies in many contexts. They are considered the gold standard for causal inference in the biomedical fields and many social…

The integration of Differential Privacy (DP) with diffusion models (DMs) presents a promising yet challenging frontier, particularly due to the substantial memorization capabilities of DMs that pose significant privacy risks. Differential…

Synthetic tabular data enables sharing and analysis of sensitive records, but its practical deployment requires balancing distributional fidelity, downstream utility, and privacy protection. We study a simple, model agnostic post processing…

This paper introduces Anticipatory Reinforcement Learning (ARL), a novel framework designed to bridge the gap between non-Markovian decision processes and classical reinforcement learning architectures, specifically under the constraint of…

Machine Learning (ML) is accelerating progress across fields and industries, but relies on accessible and high-quality training data. Some of the most important datasets are found in biomedical and financial domains in the form of…

In recent years, formal methods of privacy protection such as differential privacy (DP), capable of deployment to data-driven tasks such as machine learning (ML), have emerged. Reconciling large-scale ML with the closed-form reasoning…

The widespread use of big data across sectors has raised major privacy concerns, especially when sensitive information is shared or analyzed. Regulations such as GDPR and HIPAA impose strict controls on data handling, making it difficult to…

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…

We present a novel method for publishing differentially private synthetic attributed graphs. Unlike preceding approaches, our method is able to preserve the community structure of the original graph without sacrificing the ability to…

The study of privacy-preserving Natural Language Processing (NLP) has gained rising attention in recent years. One promising avenue studies the integration of Differential Privacy in NLP, which has brought about innovative methods in a…

Texts convey sophisticated knowledge. However, texts also convey sensitive information. Despite the success of general-purpose language models and domain-specific mechanisms with differential privacy (DP), existing text sanitization…

Large Language models (LLMs) are achieving state-of-the-art performance in many different downstream tasks. However, the increasing urgency of data privacy puts pressure on practitioners to train LLMs with Differential Privacy (DP) on…

Controllable Text Generation (CTG) has obtained great success due to its fine-grained generation ability obtained by focusing on multiple attributes. However, most existing CTG researches overlook how to utilize the attribute entanglement…

Synthetic data has gained significant momentum thanks to sophisticated machine learning tools that enable the synthesis of high-dimensional datasets. However, many generation techniques do not give the data controller control over what…

Privacy is an important concern when building statistical models on data containing personal information. Differential privacy offers a strong definition of privacy and can be used to solve several privacy concerns (Dwork et al., 2014).…

Sharing health and behavioral data raises significant privacy concerns, as conventional de-identification methods are susceptible to privacy attacks. Differential Privacy (DP) provides formal guarantees against re-identification risks, but…

Automatic speech recognition (ASR) has recently become an important challenge when using deep learning (DL). It requires large-scale training datasets and high computational and storage resources. Moreover, DL techniques and machine…