RT Journal Article
T1 Physics solutions for machine learning privacy leaks
A1 Pozas Kerstjens, Alejandro
A1 Hernández Santana, Senaida
A1 Pareja Monturiol, José Ramón
A1 Castrillón López, Marco
A1 Scarpa, Giannicola
A1 Gonzalez Guillen, Carlos E.
A1 Pérez García, David
AB Machine learning systems are becoming more and more ubiquitous in increasingly complex areas, including cutting-edge scientific research. The opposite is also true: the interest in better understanding the inner workings of machine learning systems motivates their analysis under the lens of different scientific disciplines. Physics is particularly successful in this, due to its ability to describe complex dynamical systems. While explanations of phenomena in machine learning based  physics are increasingly present, examples of direct application of notions akin to physics in order to improve machine learning systems are more scarce. Here we provide one such pplication in the problem of developing algorithms that preserve the privacy of the manipulated data, which is especially important in tasks such as the processing of medical records. We develop well-defined conditions to guarantee robustness to specific types of privacy leaks, and rigorously prove that such conditions are satisfied by tensor-network architectures. These are inspired by the efficient representation of quantum many-body systems, and have shown to compete and even surpass traditional machine learning architectures in certain cases. Given the growing expertise in training tensornetwork architectures, these results imply that one may not have to be forced to make a choice between accuracy in prediction and ensuring the privacy of the information processed.
YR 2022
FD 2022
LK https://hdl.handle.net/20.500.14352/71696
UL https://hdl.handle.net/20.500.14352/71696
LA eng
NO Unión Europea. Horizonte 2020
NO Ministerio de Ciencia e Innovación (MICINN)
NO Comunidad de Madrid
NO Centro de Excelencia Severo Ochoa
DS Docta Complutense
RD 7 abr 2025