Related papers: Transparent Anonymization: Thwarting Adversaries W…

In distributed learning settings, models are iteratively updated with shared gradients computed from potentially sensitive user data. While previous work has studied various privacy risks of sharing gradients, our paper aims to provide a…

In recent years, the data mining techniques have met a serious challenge due to the increased concerning and worries of the privacy, that is, protecting the privacy of the critical and sensitive data. Different techniques and algorithms…

LLM agents increasingly draft messages on behalf of users, yet users routinely overshare sensitive information and disagree on what counts as private. Existing systems support only suppression (omitting sensitive information) and…

Skeleton-based action recognition attracts practitioners and researchers due to the lightweight, compact nature of datasets. Compared with RGB-video-based action recognition, skeleton-based action recognition is a safer way to protect the…

Many commonly used learning algorithms work by iteratively updating an intermediate solution using one or a few data points in each iteration. Analysis of differential privacy for such algorithms often involves ensuring privacy of each step…

Rather than anonymizing social graphs by generalizing them to super nodes/edges or adding/removing nodes and edges to satisfy given privacy parameters, recent methods exploit the semantics of uncertain graphs to achieve privacy protection…

Sharing or publishing social network data while accounting for privacy of individuals is a difficult task due to the interconnectedness of nodes in networks. A key question in k-anonymity, a widely studied notion of privacy, is how to…

This paper primarily addresses the issue of identifying all possible levels of digital anonymity, thereby allowing electronic services and mechanisms to be categorised. For this purpose, we sophisticate the generic idea of anonymity and,…

Normalizing flow models have risen as a popular solution to the problem of density estimation, enabling high-quality synthetic data generation as well as exact probability density evaluation. However, in contexts where individuals are…

Publishing social network data for research purposes has raised serious concerns for individual privacy. There exist many privacy-preserving works that can deal with different attack models. In this paper, we introduce a novel privacy…

Privacy is a fundamental human right. Data privacy is protected by different regulations, such as GDPR. However, modern large language models require a huge amount of data to learn linguistic variations, and the data often contains private…

Data generalization is a powerful technique for sanitizing multi-attribute data for publication. In a multidimensional model, a subset of attributes called the quasi-identifiers (QI) are used to define the space and a generalization scheme…

The advancement of large language models (LLMs) has significantly enhanced the ability to effectively tackle various downstream NLP tasks and unify these tasks into generative pipelines. On the one hand, powerful language models, trained on…

How can we learn a representation with high predictive power while preserving user privacy? We present an adversarial representation learning method for sanitizing sensitive content from the learned representation. Specifically, we…

Recently, the permutation paradigm has been proposed in data anonymization to describe any micro data masking method as permutation, paving the way for performing meaningful analytical comparisons of methods, something that is difficult…

The curse of dimensionality has remained a challenge for a wide variety of algorithms in data mining, clustering, classification and privacy. Recently, it was shown that an increasing dimensionality makes the data resistant to effective…

Automated decision systems are increasingly used to make consequential decisions in people's lives. Due to the sensitivity of the manipulated data as well as the resulting decisions, several ethical concerns need to be addressed for the…

Security, privacy, and fairness have become critical in the era of data science and machine learning. More and more we see that achieving universally secure, private, and fair systems is practically impossible. We have seen for example how…

A dynamic algorithm against an adaptive adversary is required to be correct when the adversary chooses the next update after seeing the previous outputs of the algorithm. We obtain faster dynamic algorithms against an adaptive adversary and…

Adversarial attacks can mislead neural network classifiers. The defense against adversarial attacks is important for AI safety. Adversarial purification is a family of approaches that defend adversarial attacks with suitable pre-processing.…