相关论文: Worst-Case Background Knowledge for Privacy-Preser…

Process mining employs event data extracted from different types of information systems to discover and analyze actual processes. Event data often contain highly sensitive information about the people who carry out activities or the people…

In the last years we have witnessed the appearance of a variety of strategies to design optimal location privacy-preserving mechanisms, in terms of maximizing the adversary's expected error with respect to the users' whereabouts. In this…

The tension between persuasion and privacy preservation is common in real-world settings. Online platforms should protect the privacy of web users whose data they collect, even as they seek to disclose information about these data to…

Transparency and explainability are two important aspects to be considered when employing black-box machine learning models in high-stake applications. Providing counterfactual explanations is one way of catering this requirement. However,…

Using a broadcast channel to transmit clients' data requests may impose privacy risks. In this paper, we address such privacy concerns in the index coding framework. We show how a malicious client can infer some information about the…

This paper is concerned with the security problem for interconnected systems, where each subsystem is required to detect local attacks using locally available information and the information received from its neighboring subsystems.…

Data sharing between different organizations is an essential process in today's connected world. However, recently there were many concerns about data sharing as sharing sensitive information can jeopardize users' privacy. To preserve the…

Given a query result of a big database, why-provenance can be used to calculate the necessary part of this database, consisting of so-called witnesses. If this database consists of personal data, privacy protection has to prevent the…

In sensitive domains such as medical and legal, protecting sensitive information is critical, with protective laws strictly prohibiting the disclosure of personal data. This poses challenges for sharing valuable data such as medical reports…

This paper describes privacy-preserving approaches for the statistical analysis. It describes motivations for privacy-preserving approaches for the statistical analysis of sensitive data, presents examples of use cases where such methods…

Fine-tuning has emerged as a critical process in leveraging Large Language Models (LLMs) for specific downstream tasks, enabling these models to achieve state-of-the-art performance across various domains. However, the fine-tuning process…

We identify a novel phenomenon in language models: benign fine-tuning of frontier models can lead to privacy collapse. We find that diverse, subtle patterns in training data can degrade contextual privacy, including optimisation for…

In machine learning, boosting is one of the most popular methods that designed to combine multiple base learners to a superior one. The well-known Boosted Decision Tree classifier, has been widely adopted in many areas. In the big data era,…

Traffic analysis is a type of attack on secure communications systems, in which the adversary extracts useful patterns and information from the observed traffic. This paper improves and extends an efficient traffic analysis attack, called…

For systems whose states implicate sensitive information, their privacy is of great concern. While notions like differential privacy have been successfully introduced to dynamical systems, it is still unclear how a system's privacy can be…

An attacker can gain information of a user by analyzing its network traffic. The size of transferred data leaks information about the file being transferred or the service being used, and this is particularly revealing when the attacker has…

The problem of publishing privacy-guaranteed data for hypothesis testing is studied using the maximal leakage (ML) as a metric for privacy and the type-II error exponent as the utility metric. The optimal mechanism (random mapping) that…

Large language models (LLMs) are complex artificial intelligence systems capable of understanding, generating and translating human language. They learn language patterns by analyzing large amounts of text data, allowing them to perform…

Data poisoning attacks aim to manipulate the model produced by a learning algorithm by adversarially modifying the training set. We consider differential privacy as a defensive measure against this type of attack. We show that such learners…

The discourse on privacy risks in Large Language Models (LLMs) has disproportionately focused on verbatim memorization of training data, while a constellation of more immediate and scalable privacy threats remain underexplored. This…