Related papers: DP-Fusion: Token-Level Differentially Private Infe…
Text-to-image diffusion models have been shown to suffer from sample-level memorization, possibly reproducing near-perfect replica of images that they are trained on, which may be undesirable. To remedy this issue, we develop the first…
Differentially private in-context learning (DP-ICL) has recently become an active research topic due to the inherent privacy risks of in-context learning. However, existing approaches overlook a critical component of modern large language…
Large language models (LLMs) have become the backbone of modern natural language processing but pose privacy concerns about leaking sensitive training data. Membership inference attacks (MIAs), which aim to infer whether a sample is…
Fine-tuning is a common and effective method for tailoring large language models (LLMs) to specialized tasks and applications. In this paper, we study the privacy implications of fine-tuning LLMs on user data. To this end, we consider a…
As Large Language Models (LLMs) proliferate, developing privacy safeguards for these models is crucial. One popular safeguard involves training LLMs in a differentially private manner. However, such solutions are shown to be computationally…
We introduce DP-FinDiff, a differentially private diffusion framework for synthesizing mixed-type tabular data. DP-FinDiff employs embedding-based representations for categorical features, reducing encoding overhead and scaling to…
Differential privacy (DP) has been accepted as a rigorous criterion for measuring the privacy protection offered by random mechanisms used to obtain statistics or, as we will study here, synthetic datasets from confidential data. Methods to…
The community explored to build private inference frameworks for transformer-based large language models (LLMs) in a server-client setting, where the server holds the model parameters and the client inputs its private data (or prompt) for…
This article introduces differentially private log-location-scale (DP-LLS) regression models, which incorporate differential privacy into LLS regression through the functional mechanism. The proposed models are established by injecting…
Differentially private (DP) mechanisms face the challenge of providing accurate results while protecting their inputs: the privacy-utility trade-off. A simple but powerful technique for DP adds noise to sensitivity-bounded query outputs to…
Differentially private stochastic gradient descent (DP-SGD) adds noise to gradients in back-propagation, safeguarding training data from privacy leakage, particularly membership inference. It fails to cover (inference-time) threats like…
Differential privacy (DP) is the prevailing technique for protecting user data in machine learning models. However, deficits to this framework include a lack of clarity for selecting the privacy budget $\epsilon$ and a lack of…
Differential privacy (DP) is the de facto privacy standard against privacy leakage attacks, including many recently discovered ones against large language models (LLMs). However, we discovered that LLMs could reconstruct the altered/removed…
Large Language Models (LLMs) are increasingly adopted across domains such as education, healthcare, and finance. In healthcare, LLMs support tasks including disease diagnosis, abnormality classification, and clinical decision-making. Among…
Data engineering often requires accuracy (utility) constraints on results, posing significant challenges in designing differentially private (DP) mechanisms, particularly under stringent privacy parameter $\epsilon$. In this paper, we…
Large Language Models (LLMs) have demonstrated advanced capabilities in both text generation and comprehension, and their application to data archives might facilitate the privatization of sensitive information about the data subjects. In…
Protecting large language models from privacy leakage is becoming increasingly crucial with their wide adoption in real-world products. Yet applying differential privacy (DP), a canonical notion with provable privacy guarantees for machine…
Language modeling is a keystone task in natural language processing. When training a language model on sensitive information, differential privacy (DP) allows us to quantify the degree to which our private data is protected. However,…
Differential privacy (DP) techniques can be applied to the federated learning model to protect data privacy against inference attacks to communication among the learning agents. The DP techniques, however, hinder achieving a greater…
We explore how private synthetic text can be generated by suitably prompting a large language model (LLM). This addresses a challenge for organizations like hospitals, which hold sensitive text data like patient medical records, and wish to…