Related papers: Differentially Private Motif-Preserving Multi-moda…

Learning with relational and network-structured data is increasingly vital in sensitive domains where protecting the privacy of individual entities is paramount. Differential Privacy (DP) offers a principled approach for quantifying privacy…

In modern settings of data analysis, we may be running our algorithms on datasets that are sensitive in nature. However, classical machine learning and statistical algorithms were not designed with these risks in mind, and it has been…

Differential privacy has been used to privately calculate numerous network properties, but existing approaches often require the development of a new privacy mechanism for each property of interest. Therefore, we present a framework for…

Differentially private (DP) image synthesis aims to generate artificial images that retain the properties of sensitive images while protecting the privacy of individual images within the dataset. Despite recent advancements, we find that…

Large language models (LLMs) have significantly transformed natural language understanding and generation, but they raise privacy concerns due to potential exposure of sensitive information. Studies have highlighted the risk of information…

Models need to be trained with privacy-preserving learning algorithms to prevent leakage of possibly sensitive information contained in their training data. However, canonical algorithms like differentially private stochastic gradient…

Privacy concerns have led to a surge in the creation of synthetic datasets, with diffusion models emerging as a promising avenue. Although prior studies have performed empirical evaluations on these models, there has been a gap in providing…

Large language models (LLMs) do not preserve privacy at inference-time. The LLM's outputs can inadvertently reveal information about the model's context, which presents a privacy challenge when the LLM is augmented via tools or databases…

Vision-language models are increasingly applied to sensitive domains such as medical imaging and personal photographs, yet existing differentially private methods for in-context learning are limited to few-shot, text-only settings because…

Local Differential Privacy (LDP) enables massive data collection and analysis while protecting end users' privacy against untrusted aggregators. It has been applied to various data types (e.g., categorical, numerical, and graph data) and…

Deep hashing has recently received attention in cross-modal retrieval for its impressive advantages. However, existing hashing methods for cross-modal retrieval cannot fully capture the heterogeneous multi-modal correlation and exploit the…

In this work we describe the High-Dimensional Matrix Mechanism (HDMM), a differentially private algorithm for answering a workload of predicate counting queries. HDMM represents query workloads using a compact implicit matrix representation…

Cross-attention has emerged as a cornerstone module in modern artificial intelligence, underpinning critical applications such as retrieval-augmented generation (RAG), system prompting, and guided stable diffusion. However, this is a rising…

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…

Concern about how to aggregate sensitive user data without compromising individual privacy is a major barrier to greater availability of data. The model of differential privacy has emerged as an accepted model to release sensitive…

We address the problem of synthesizing distorting mechanisms that maximize privacy of stochastic dynamical systems. Information about the system state is obtained through sensor measurements. This data is transmitted to a remote station…

Honey Encryption is an approach to encrypt the messages using low min-entropy keys, such as weak passwords, OTPs, PINs, credit card numbers. The ciphertext is produces, when decrypted with any number of incorrect keys, produces…

Graph embedding has become a powerful tool for learning latent representations of nodes in a graph. Despite its superior performance in various graph-based machine learning tasks, serious privacy concerns arise when the graph data contains…

Differential privacy provides the first theoretical foundation with provable privacy guarantee against adversaries with arbitrary prior knowledge. The main idea to achieve differential privacy is to inject random noise into statistical…

It is currently difficult to distill discrete diffusion models. In contrast, continuous diffusion literature has many distillation approaches methods that can reduce sampling steps to a handful. Our method, Discrete Moment Matching…