Related papers: Privug: Using Probabilistic Programming for Quanti…
The use of personal data for training machine learning systems comes with a privacy threat and measuring the level of privacy of a model is one of the major challenges in machine learning today. Identifying training data based on a trained…
The emergence of social and technological networks has enabled rapid sharing of data and information. This has resulted in significant privacy concerns where private information can be either leaked or inferred from public data. The problem…
Probabilistic reasoning is a key aspect of both human and artificial intelligence that allows for handling uncertainty and ambiguity in decision-making. In this paper, we introduce a new numerical reasoning task under uncertainty for large…
Our ability to control the flow of sensitive personal information to online systems is key to trust in personal privacy on the internet. We ask how to detect, assess and defend user privacy in the face of search engine personalisation? We…
Unlike other industries in which intellectual property is patentable, the financial industry relies on trade secrecy to protect its business processes and methods, which can obscure critical financial risk exposures from regulators and the…
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…
Large Language Models (LLMs) are widely used in sensitive domains, including healthcare, finance, and legal services, raising concerns about potential private information leaks during inference. Privacy extraction attacks, such as…
Recent developments in cloud storage architectures have originated new models of online storage as cooperative storage systems and interconnected clouds. Such distributed environments involve many organizations, thus ensuring…
The emerging public awareness and government regulations of data privacy motivate new paradigms of collecting and analyzing data that are transparent and acceptable to data owners. We present a new concept of privacy and corresponding data…
Software logs, generated during the runtime of software systems, are essential for various development and analysis activities, such as anomaly detection and failure diagnosis. However, the presence of sensitive information in these logs…
Differential privacy is becoming a gold standard for privacy research; it offers a guaranteed bound on loss of privacy due to release of query results, even under worst-case assumptions. The theory of differential privacy is an active…
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…
We present d3p, a software package designed to help fielding runtime efficient widely-applicable Bayesian inference under differential privacy guarantees. d3p achieves general applicability to a wide range of probabilistic modelling…
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…
Online social networks have enabled new methods and modalities of collaboration and sharing. These advances bring privacy concerns: online social data is more accessible and persistent and simultaneously less contextualized than traditional…
Synthetic data is a promising approach to privacy protection in many contexts. A Bayesian synthesis model, also known as a synthesizer, simulates synthetic values of sensitive variables from their posterior predictive distributions. The…
Algorithmic fairness and privacy are essential pillars of trustworthy machine learning. Fair machine learning aims at minimizing discrimination against protected groups by, for example, imposing a constraint on models to equalize their…
Differential privacy is a notion of privacy that has become very popular in the database community. Roughly, the idea is that a randomized query mechanism provides sufficient privacy protection if the ratio between the probabilities of two…
Users interacting with large language models (LLMs) under their real identifiers often unknowingly risk disclosing private information. Automatically notifying users whether their queries leak privacy and which phrases leak what private…
Program obfuscation is a widely employed approach for software intellectual property protection. However, general obfuscation methods (e.g., lexical obfuscation, control obfuscation) implemented in mainstream obfuscation tools are heuristic…