Related papers: PEEPLL: Privacy-Enhanced Event Pseudonymisation wi…
This paper investigates the relation between three different notions of privacy: identifiability, differential privacy and mutual-information privacy. Under a unified privacy-distortion framework, where the distortion is defined to be the…
Conversational agents are increasingly woven into individuals' personal lives, yet users often underestimate the privacy risks associated with them. The moment users share information with these agents-such as large language models…
Differential privacy is a popular privacy-enhancing technology that has been deployed both in industry and government agencies. Unfortunately, existing explanations of differential privacy fail to set accurate privacy expectations for data…
Differential privacy allows bounding the influence that training data records have on a machine learning model. To use differential privacy in machine learning, data scientists must choose privacy parameters $(\epsilon,\delta)$. Choosing…
Differential Privacy (DP) is a well-established framework to quantify privacy loss incurred by any algorithm. Traditional formulations impose a uniform privacy requirement for all users, which is often inconsistent with real-world scenarios…
Recently, privacy issues in web services that rely on users' personal data have raised great attention. Unlike existing privacy-preserving technologies such as federated learning and differential privacy, we explore another way to mitigate…
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…
Privacy-preserving distributed processing has received considerable attention recently. The main purpose of these algorithms is to solve certain signal processing tasks over a network in a decentralised fashion without revealing…
When users submit queries to Large Language Models (LLMs), their prompts can often contain sensitive data, forcing a difficult choice: Send the query to a powerful proprietary LLM providers to achieving state-of-the-art performance and risk…
Differential privacy provides a formal approach to privacy of individuals. Applications of differential privacy in various scenarios, such as protecting users' original utterances, must satisfy certain mathematical properties. Our…
Preserving privacy of continuous and/or high-dimensional data such as images, videos and audios, can be challenging with syntactic anonymization methods which are designed for discrete attributes. Differential privacy, which provides a more…
Privacy-Preserving Federated Learning (PPFL) enables multiple clients to collaboratively train models by submitting secreted model updates. Nonetheless, PPFL is vulnerable to data poisoning attacks due to its distributed training paradigm…
The decentralized nature of federated learning, that often leverages the power of edge devices, makes it vulnerable to attacks against privacy and security. The privacy risk for a peer is that the model update she computes on her private…
The guarantees of security and privacy defenses are often strengthened by relaxing the assumptions made about attackers or the context in which defenses are deployed. Such relaxations can be a highly worthwhile topic of exploration---even…
Differential Privacy (DP) is a well-established framework to quantify privacy loss incurred by any algorithm. Traditional DP formulations impose a uniform privacy requirement for all users, which is often inconsistent with real-world…
Privacy-preserving machine learning algorithms are crucial for the increasingly common setting in which personal data, such as medical or financial records, are analyzed. We provide general techniques to produce privacy-preserving…
In this paper, we study local information privacy (LIP), and design LIP based mechanisms for statistical aggregation while protecting users' privacy without relying on a trusted third party. The notion of context-awareness is incorporated…
Objective: The use of routinely-acquired medical data for research purposes requires the protection of patient confidentiality via data anonymisation. The objective of this work is to calculate the risk of re-identification arising from a…
Large language models (LLMs) have demonstrated exceptional capabilities in text understanding and generation, and they are increasingly being utilized across various domains to enhance productivity. However, due to the high costs of…
Individual Differential Privacy (iDP) promises users control over their privacy, but this promise can be broken in practice. We reveal a previously overlooked vulnerability in sampling-based iDP mechanisms: while conforming to the iDP…