Publishing neural networks in drug discovery might compromise training data privacy

Abstract This study investigates the risks of exposing confidential chemical structures when machine learning models trained on these structures are made publicly available. We use membership inference attacks, a common method to assess privacy that is largely unexplored in the context of drug disco...

תיאור מלא

מידע ביבליוגרפי

Principais autores:	Fabian P. Krüger, Johan Östman, Lewis Mervin, Igor V. Tetko, Ola Engkvist
פורמט:	Artigo
שפה:	Inglês
יצא לאור:	BMC 2025-03-01
סדרה:	Journal of Cheminformatics
נושאים:	Membership inference attack Privacy Drug discovery Cheminformatics QSAR Machine learning
גישה מקוונת:	https://doi.org/10.1186/s13321-025-00982-w
תגים:	הוספת תג אין תגיות, היה/י הראשונ/ה לתייג את הרשומה!