Privacy: An Axiomatic Approach

Abstract

The increasing prevalence of large-scale data collection in modern society represents a potential threat to individual privacy. Addressing this threat, for example through privacy-enhancing technologies (PETs), requires a rigorous definition of what exactly is being protected, that is, of privacy itself. In this work, we formulate an axiomatic definition of privacy based on quantifiable and irreducible information flows. Our definition synthesizes prior work from the domain of social science with a contemporary understanding of PETs such as differential privacy (DP). Our work highlights the fact that the inevitable difficulties of protecting privacy in practice are fundamentally information-theoretic. Moreover, it enables quantitative reasoning about PETs based on what they are protecting, thus fostering objective policy discourse about their societal implementation.

Encrypted federated learning for secure decentralized collaboration in cancer image analysis

“…However, FL and SL have an important shortcoming: during training, weight updates must be shared and information about the underlying data can be extracted from these weight updates as shown in our study. Such techniques should thus not be considered privacy techniques, but techniques for preserving data governance( Ziller et al., 2022 ). Since medical data is highly sensitive and since data privacy laws forbid the use of data in such environments, where private data can be extracted, this critically limits the applicability of collaborative learning schemes and prevents the development of powerful AI models in cancer diagnosis and treatment.…”

Encrypted federated learning for secure decentralized collaboration in cancer image analysis

“…However, FL and SL have an important shortcoming: during training, weight updates must be shared and information about the underlying data can be extracted from these weight updates as shown in our study. Such techniques should thus not be considered privacy techniques, but techniques for preserving data governance 32 . Since medical data is highly sensitive and since data privacy laws forbid the use of data in such environments, where private data can be extracted, this critically limits the applicability of collaborative learning schemes and prevents the development of powerful AI models in cancer diagnosis and treatment.…”