KIT | KIT-Bibliothek | Impressum | Datenschutz

Trade-offs Between Privacy-Preserving and Explainable Machine Learning in Healthcare

Budig, Tobias; Dietz, Alexander; Herrmann, Selina

Abstract:
Background: Machine Learning has enormous potential for applications in various fields. Explainability and privacy are two key questions when training a Machine Learning model especially in critical information infrastructure such as the healthcare sector.
Objective: The goal of this paper is to identify the current state of research and possible trade-offs between explainability and privacy of Machine Learning models. Furthermore, the aim was to identify possible ways of implementing explainability methods in Federated Learning, a privacy-preserving setting.
Methods: First, we have conducted a systematic literature review to identify possible trade-offs. Second, we evaluated and selected methods that one can theoretically implement without risking privacy in a Federated Learning application with a focus on medical image analysis.
Results: Our results show that only a few researchers have so far been discussing possible trade-offs between explainable and privacy-preserving Machine Learning. The three relevant papers show that there is a natural trade-off, and a higher level of explainability can make a model more vulnerable to attacks and therefore have a higher risk of privacy leakage. ... mehr


Verlagsausgabe §
DOI: 10.5445/IR/1000138902
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Angewandte Informatik und Formale Beschreibungsverfahren (AIFB)
Publikationstyp Buchaufsatz
Publikationsmonat/-jahr 10.2021
Sprache Englisch
Identifikator KITopen-ID: 1000139018
Erschienen in cii Student Papers - 2021. Ed.: A. Sunyaev
Verlag Karlsruher Institut für Technologie (KIT)
Seiten 59-72
Schlagwörter machine learning, privacy-preserving, XAI, federated learning, trade-offs
Relationen in KITopen
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page