EUVIMEDEUVIMED entdecken
Open Access · CC BY 3.0

Censoring chemical data to mitigate dual use risk

Quintina Campbell iD, Jonathan Herington iD, Andrew D White iD

Digital Discovery · 2026 · 5 (8) · 3275-3289

DOI: 10.1039/d5dd00512d ↗

Kurz gefasst

Fachartikel in der Zeitschrift Digital Discovery, 2026. Verfasst von Quintina Campbell und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Chemical Engineering, University of Rochester Rochester New York USA. Die Arbeit nennt 93 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 3.0). Gefördert von: NIGMS NIH HHS, NCATS NIH HHS, National Institute of General Medical Sciences.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Selectively noising chemical datasets reduces the model accuracy in sensitive regions, offering a data-level approach to mitigate dual use risks in predictive chemistry.

Autor:innen und Institutionen

  • Department of Chemical Engineering, University of Rochester Rochester New York USA.
  • Department of Health Humanities & Bioethics, University of Rochester Rochester New York USA jonathan.herington@rochester.edu.
  • Edison Scientific Inc. San Francisco CA USA andrew@edisonscientific.com.

ORCID-Profile: Quintina Campbell, Jonathan Herington, Andrew D White

Förderung

  • NIGMS NIH HHS
  • NCATS NIH HHS
  • National Institute of General Medical Sciences
  • National Center for Advancing Translational Sciences
  • Lawrence Livermore National Laboratory

Zitieren

APA

Campbell, Q., Herington, J., & White, A. D. (2026). Censoring chemical data to mitigate dual use risk. Digital Discovery, 5(8), 3275-3289. https://doi.org/10.1039/d5dd00512d

Vancouver

Campbell Q, Herington J, White AD. Censoring chemical data to mitigate dual use risk. Digital Discovery. 2026;5(8):3275-3289. doi:10.1039/d5dd00512d

BibTeX
@article{Campbell2026,
  author = {Campbell, Quintina and Herington, Jonathan and White, Andrew D},
  title = {Censoring chemical data to mitigate dual use risk},
  journal = {Digital Discovery},
  year = {2026},
  volume = {5},
  number = {8},
  pages = {3275--3289},
  doi = {10.1039/d5dd00512d}
}
Kostenlos starten →