Related papers: Visual Privacy Auditing with Diffusion Models

Personalized diffusion models (PDMs) have become prominent for adapting pre-trained text-to-image models to generate images of specific subjects using minimal training data. However, PDMs are susceptible to minor adversarial perturbations,…

Privacy protection has become a top priority as the proliferation of AI techniques has led to widespread collection and misuse of personal data. Anonymization and visual identity information hiding are two important facial privacy…

Collaborative learning has gained great popularity due to its benefit of data privacy protection: participants can jointly train a Deep Learning model without sharing their training sets. However, recent works discovered that an adversary…

We explore Reconstruction Robustness (ReRo), which was recently proposed as an upper bound on the success of data reconstruction attacks against machine learning models. Previous research has demonstrated that differential privacy (DP)…

Tabular data plays an important role in many fields and industries, including those with elevated privacy considerations and risks. As such, there is a rising interest in generating high-quality synthetic proxies for real tabular data as a…

Auditing mechanisms for differential privacy use probabilistic means to empirically estimate the privacy level of an algorithm. For private machine learning, existing auditing mechanisms are tight: the empirical privacy estimate (nearly)…

We explore user-level gradient inversion as a new attack surface in distributed learning. We first investigate existing attacks on their ability to make inferences about private information beyond training data reconstruction. Motivated by…

Diffusion models have been remarkably successful in data synthesis. However, when these models are applied to sensitive datasets, such as banking and human face data, they might bring up severe privacy concerns. This work systematically…

Federated Learning (FL) enables collaborative training of machine learning models across distributed clients without sharing raw data, ostensibly preserving data privacy. Nevertheless, recent studies have revealed critical vulnerabilities…

As deep learning-based, data-driven information extraction systems become increasingly integrated into modern document processing workflows, one primary concern is the risk of malicious leakage of sensitive private data from these systems.…

Differential Privacy (DP) is a mathematical framework that is increasingly deployed to mitigate privacy risks associated with machine learning and statistical analyses. Despite the growing adoption of DP, its technical privacy parameters do…

The memorization of training data by neural networks raises pressing concerns for privacy and security. Recent work has shown that, under certain conditions, portions of the training set can be reconstructed directly from model parameters.…

Reconstruction attacks against federated learning (FL) aim to reconstruct users' samples through users' uploaded gradients. Local differential privacy (LDP) is regarded as an effective defense against various attacks, including sample…

Diffusion auction refers to an emerging paradigm of online marketplace where an auctioneer utilises a social network to attract potential buyers. Diffusion auction poses significant privacy risks. From the auction outcome, it is possible to…

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…

Data privacy protection is garnering increased attention among researchers. Diffusion models (DMs), particularly with strict differential privacy, can potentially produce images with both high privacy and visual quality. However, challenges…

Diffusion-based purification defenses leverage diffusion models to remove crafted perturbations of adversarial examples and achieve state-of-the-art robustness. Recent studies show that even advanced attacks cannot break such defenses…

Modern computer vision services often require users to share raw feature descriptors with an untrusted server. This presents an inherent privacy risk, as raw descriptors may be used to recover the source images from which they were…

Diffusion models have shown to be strong representation learners, showcasing state-of-the-art performance across multiple domains. Aside from accelerated sampling, DDIM also enables the inversion of real images back to their latent codes. A…

Deep hashing improves retrieval efficiency through compact binary codes, yet it introduces severe and often overlooked privacy risks. The ability to reconstruct original training data from hash codes could lead to serious threats such as…