相关论文: Inspecting the Representation Manifold of Differen…

We consider a refinement of differential privacy --- per instance differential privacy (pDP), which captures the privacy of a specific individual with respect to a fixed data set. We show that this is a strict generalization of the standard…

In this paper, we investigate the diversity aspect of paraphrase generation. Prior deep learning models employ either decoding methods or add random input noise for varying outputs. We propose a simple method Diverse Paraphrase Generation…

The privacy concerns associated with the use of Large Language Models (LLMs) have grown recently with the development of LLMs such as ChatGPT. Differential Privacy (DP) techniques are explored in existing work to mitigate their privacy…

An important problem in deep learning is the privacy and security of neural networks (NNs). Both aspects have long been considered separately. To date, it is still poorly understood how privacy enhancing training affects the robustness of…

Large language models trained on clinical text risk exposing sensitive patient information, yet differential privacy (DP) methods often severely degrade the diagnostic accuracy needed for deployment. Despite rapid progress in DP…

A central question in cognitive science is whether conceptual representations converge onto a shared manifold to support generalization, or diverge into orthogonal subspaces to minimize task interference. While prior work has discovered…

As sufficient data are not always publically accessible for model training, researchers exploit limited data with advanced learning algorithms or expand the dataset via data augmentation (DA). Conducting DA in private domain requires…

High-dimensional representations for words, text, images, knowledge graphs and other structured data are commonly used in different paradigms of machine learning and data mining. These representations have different degrees of…

Personalized privacy becomes critical in deep learning for Trustworthy AI. While Differentially Private Stochastic Gradient Descent (DP-SGD) is widely used in deep learning methods supporting privacy, it provides the same level of privacy…

Deep learning models for NLP tasks are prone to variants of privacy attacks. To prevent privacy leakage, researchers have investigated word-level perturbations, relying on the formal guarantees of differential privacy (DP) in the embedding…

Differential privacy (DP) considers a scenario, where an adversary has almost complete information about the entries of a database This worst-case assumption is likely to overestimate the privacy thread for an individual in real life.…

Differential privacy (DP) is a compelling privacy definition that explains the privacy-utility tradeoff via formal, provable guarantees. Inspired by recent progress toward general-purpose data release algorithms, we propose a private…

Differential privacy provides a formal approach to privacy of individuals. Applications of differential privacy in various scenarios, such as protecting users' original utterances, must satisfy certain mathematical properties. Our…

We study the problem of performing counting queries at different levels in hierarchical structures while preserving individuals' privacy. Motivated by applications, we propose a new error measure for this problem by considering a…

In differentially private (DP) machine learning, the privacy guarantees of DP mechanisms are often reported and compared on the basis of a single $(\varepsilon, \delta)$-pair. This practice overlooks that DP guarantees can vary…

We propose a novel and systematic differentially private (DP) inference framework for non-Euclidean data. First, we design two types of DP mechanisms for the Fr\'echet mean and variance with i.i.d. Riemannian manifold-valued data, tailored…

Many forms of sensitive data, such as web traffic, mobility data, or hospital occupancy, are inherently sequential. The standard method for training machine learning models while ensuring privacy for units of sensitive information, such as…

We propose the notion of empirical privacy variance and study it in the context of differentially private fine-tuning of language models. Specifically, we show that models calibrated to the same $(\varepsilon, \delta)$-DP guarantee using…

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…

Applying differential privacy (DP) by means of the DP-SGD algorithm to protect individual data points during training is becoming increasingly popular in NLP. However, the choice of granularity at which DP is applied is often neglected. For…