Related papers: PEEPLL: Privacy-Enhanced Event Pseudonymisation wi…

In a typical Event-Based Surveillance setting, a stream of web documents is continuously monitored for disease reporting. A structured representation of the disease reporting events is extracted from the raw text, and the events are then…

In today's digital world, casual user-generated content often contains subtle cues that may inadvertently expose sensitive personal attributes. Such risks underscore the growing importance of effective text anonymization to safeguard…

Allowing organizations to share their data for training of machine learning (ML) models without unintended information leakage is an open problem in practice. A promising technique for this still-open problem is to train models on the…

In the Open Data approach, governments and other public organisations want to share their datasets with the public, for accountability and to support participation. Data must be opened in such a way that individual privacy is safeguarded.…

A growing framework of legal and ethical requirements limit scientific and commercial evalua-tion of personal data. Typically, pseudonymization, encryption, or methods of distributed com-puting try to protect individual privacy. However,…

In this thesis we consider the problem of information hiding in the scenarios of interactive systems, statistical disclosure control, and refinement of specifications. We apply quantitative approaches to information flow in the first two…

The absence of data protection measures in software applications leads to data breaches, threatening end-user privacy and causing instabilities in organisations that developed those software. Privacy Enhancing Technologies (PETs) emerge as…

Neuromorphic vision sensors offer low latency and high dynamic range, but their deployment in public spaces raises severe data protection concerns. Recent Event-to-Video (E2V) models can reconstruct high-fidelity intensity images from…

The use of Natural Language Processing (NLP) in highstakes AI-based applications has increased significantly in recent years, especially since the emergence of Large Language Models (LLMs). However, despite their strong performance, LLMs…

Privacy-preserving process mining enables the analysis of business processes using event logs, while giving guarantees on the protection of sensitive information on process stakeholders. To this end, existing approaches add noise to the…

The shuffle model is recently proposed to address the issue of severe utility loss in Local Differential Privacy (LDP) due to distributed data randomization.In the shuffle model, a shuffler is utilized to break the link between the user…

Voice anonymisation aims to conceal the voice identity of speakers in speech recordings. Privacy protection is usually estimated from the difficulty of using a speaker verification system to re-identify the speaker post-anonymisation.…

To protect user privacy in data analysis, a state-of-the-art strategy is differential privacy in which scientific noise is injected into the real analysis output. The noise masks individual's sensitive information contained in the dataset.…

With the widespread application of large language models (LLMs), user privacy protection has become a significant research topic. Existing privacy preference modeling methods often rely on large-scale user data, making effective privacy…

This paper aims at answering the following two questions in privacy-preserving data analysis and publishing: What formal privacy guarantee (if any) does $k$-anonymization provide? How to benefit from the adversary's uncertainty about the…

Federated learning enables users to collaboratively train a machine learning model over their private datasets. Secure aggregation protocols are employed to mitigate information leakage about the local datasets. This setup, however, still…

We introduce Epsilon*, a new privacy metric for measuring the privacy risk of a single model instance prior to, during, or after deployment of privacy mitigation strategies. The metric requires only black-box access to model predictions,…

Local Differential Privacy (LDP) protocols enable an untrusted data collector to perform privacy-preserving data analytics. In particular, each user locally perturbs its data to preserve privacy before sending it to the data collector, who…

By inducing privacy attacks on NLP models, attackers can obtain sensitive information such as training data and model parameters, etc. Although researchers have studied, in-depth, several kinds of attacks in NLP models, they are…

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…