Related papers: PEEPLL: Privacy-Enhanced Event Pseudonymisation wi…
The rapid development of language models (LMs) brings unprecedented accessibility and usage for both models and users. On the one hand, powerful LMs achieve state-of-the-art performance over numerous downstream NLP tasks. On the other hand,…
Large language models (LLMs) are primarily accessed via commercial APIs, but this often requires users to expose their data to service providers. In this paper, we explore how users can stay in control of their data by using privacy…
This work examines a novel question: how much randomness is needed to achieve local differential privacy (LDP)? A motivating scenario is providing {\em multiple levels of privacy} to multiple analysts, either for distribution or for…
Today's massive scale of data collection coupled with recent surges of consumer data leaks has led to increased attention towards data privacy and related risks. Conventional data privacy protection systems focus on reducing custodial risk…
While web agents gained popularity by automating web interactions, their requirement for interface access introduces significant privacy risks that are understudied, particularly from users' perspective. Through a formative study (N=15), we…
LLM agents have begun to appear as personal assistants, customer service bots, and clinical aides. While these applications deliver substantial operational benefits, they also require continuous access to sensitive data, which increases the…
We propose a practical methodology to protect a user's private data, when he wishes to publicly release data that is correlated with his private data, in the hope of getting some utility. Our approach relies on a general statistical…
User profiling is crucial in providing personalised services, as it relies on analysing user behaviour and preferences to deliver targeted services. This approach enhances user experience and promotes heightened engagement. Nevertheless,…
The rapid deployment of large language models (LLMs) in consumer applications has led to frequent exchanges of personal information. To obtain useful responses, users often share more than necessary, increasing privacy risks via…
Numerous companies have started offering services based on large language models (LLM), such as ChatGPT, which inevitably raises privacy concerns as users' prompts are exposed to the model provider. Previous research on secure reasoning…
Differential privacy protects an individual's privacy by perturbing data on an aggregated level (DP) or individual level (LDP). We report four online human-subject experiments investigating the effects of using different approaches to…
Human mobility data is a crucial resource for urban mobility management, but it does not come without personal reference. The implementation of security measures such as anonymization is thus needed to protect individuals' privacy. Often, a…
Differential privacy (DP) considers a scenario, where an adversary has almost complete information about the entries of a database This worst-case assumption is likely to overestimate the privacy thread for an individual in real life.…
To discover new insights from data, there is a growing need to share information that is often held by different organisations. One key task in data integration is the calculation of similarities between records in different databases to…
Training generative machine learning models to produce synthetic tabular data has become a popular approach for enhancing privacy in data sharing. As this typically involves processing sensitive personal information, releasing either the…
Federated Learning, as a popular paradigm for collaborative training, is vulnerable against privacy attacks. Different privacy levels regarding users' attitudes need to be satisfied locally, while a strict privacy guarantee for the global…
Location privacy-preserving mechanisms (LPPMs) have been extensively studied for protecting users' location privacy by releasing a perturbed location to third parties such as location-based service providers. However, when a user's…
Record linkage refers to the task of integrating data from two or more databases without a common identifier. MINDFIRL (MInimum Necessary Disclosure For Interactive Record Linkage) is a software system that demonstrates the tradeoff between…
Sequential data is everywhere, and it can serve as a basis for research that will lead to improved processes. For example, road infrastructure can be improved by identifying bottlenecks in GPS data, or early diagnosis can be improved by…
Network-level privacy is the Achilles heel of financial privacy in cryptocurrencies. Financial privacy amounts to achieving and maintaining blockchain- and network-level privacy. Blockchain-level privacy recently received substantial…