Related papers: Reasoning over Public and Private Data in Retrieva…

Personalized health analytics increasingly rely on population benchmarks to provide contextual insights such as ''How do I compare to others like me?'' However, cohort-based aggregation of health data introduces nontrivial privacy risks,…

An accountable algorithmic transparency report (ATR) should ideally investigate the (a) transparency of the underlying algorithm, and (b) fairness of the algorithmic decisions, and at the same time preserve data subjects' privacy. However,…

Retrieval based open-domain QA systems use retrieved documents and answer-span selection over retrieved documents to find best-answer candidates. We hypothesize that multilingual Question Answering (QA) systems are prone to information…

With the development of Big Data and cloud data sharing, privacy preserving data publishing becomes one of the most important topics in the past decade. As one of the most influential privacy definitions, differential privacy provides a…

In a Public Safety (PS) situation, agents may require critical and personally identifiable information. Therefore, not only does context and location-aware information need to be available, but also the privacy of such information should be…

The literature on differential privacy almost invariably assumes that the data to be analyzed are fully observed. In most practical applications this is an unrealistic assumption. A popular strategy to address this problem is imputation, in…

Users worldwide access massive amounts of curated data in the form of rankings on a daily basis. The societal impact of this ease of access has been studied and work has been done to propose and enforce various notions of fairness in…

In the privacy-utility tradeoff of a model trained on benchmark language and vision tasks, remarkable improvements have been widely reported with the use of pretraining on publicly available data. This is in part due to the benefits of…

Personalized AI agents rely on access to a user's digital footprint, which often includes sensitive data from private emails, chats and purchase histories. Yet this access creates a fundamental societal and privacy risk: systems lacking…

Machine learning is increasingly used in the most diverse applications and domains, whether in healthcare, to predict pathologies, or in the financial sector to detect fraud. One of the linchpins for efficiency and accuracy in machine…

Ensuring privacy during inference stage is crucial to prevent malicious third parties from reconstructing users' private inputs from outputs of public models. Despite a large body of literature on privacy preserving learning (which ensures…

Differential privacy formalises privacy-preserving mechanisms that provide access to a database. We pose the question of whether Bayesian inference itself can be used directly to provide private access to data, with no modification. The…

Suppose we would like to know all answers to a set of statistical queries C on a data set up to small error, but we can only access the data itself using statistical queries. A trivial solution is to exhaustively ask all queries in C. Can…

Post-processing immunity is a fundamental property of differential privacy: it enables arbitrary data-independent transformations to differentially private outputs without affecting their privacy guarantees. Post-processing is routinely…

Modern epidemiological analyses to understand and combat the spread of disease depend critically on access to, and use of, data. Rapidly evolving data, such as data streams changing during a disease outbreak, are particularly challenging.…

In privacy-preserving machine learning, individual parties are reluctant to share their sensitive training data due to privacy concerns. Even the trained model parameters or prediction can pose serious privacy leakage. To address these…

Considering the limited internal parametric knowledge, retrieval-augmented generation (RAG) has been widely used to extend the knowledge scope of large language models (LLMs). Despite the extensive efforts on RAG research, in existing…

A large number of services for research data management strive to adhere to the FAIR guiding principles for scientific data management and stewardship. To evaluate these services and to indicate possible improvements, use-case-centric…

Retrieval-Augmented Generation (RAG) is a promising technique for applying LLMs to proprietary domains. However, retrieved documents may contain sensitive knowledge, posing risks of privacy leakage in generative results. Thus, effectively…

Modern machine learning systems use models trained on ever-growing corpora. Typically, metadata such as ownership, access control, or licensing information is ignored during training. Instead, to mitigate privacy risks, we rely on generic…