EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhancing privacy in biosecurity with watermarked protein design

Yanshuo Chen iD, Zhengmian Hu iD, Yihan Wu, Ruibo Chen, Yongrui Jin, Marcus Zhan, Chengjin Xie, Wei Chen iD, Heng Huang iD

Bioinformatics · 2025

DOI: 10.1093/bioinformatics/btaf141 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2025. Verfasst von Yanshuo Chen und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, University of Maryland, College Park, MD 20742, United States. Hauptthemen laut MEDLINE: Proteins, Computer Security, Deep Learning, Privacy. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 16 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NSF.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation The biosecurity issue arises as the capability of deep-learning-based protein design has rapidly increased in recent years. Current regulation procedures for DNA synthesizing focus on the biosecurity but ignore the data privacy. Results We propose a general framework for adding watermarks to protein sequences designed by various autoregressive deep-learning models. Compared to current regulation procedures, watermarks also ensure robust traceability to achieve biosecurity but maintain privacy of designed sequences by local verification. Benchmarked with other watermarking techniques, the watermark detection efficiency of our method is substantially increased to be more practical in real-world scenarios. Moreover, it provides a convenient way for researchers to claim their own intellectual property since the designer’s information could be embedded into the sequence with our framework. Availability and implementation The implementation of the protein watermark framework is freely available to noncommercial users at https://github.com/poseidonchan/ProteinWatermark.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ProteinsComputer SecurityDeep LearningPrivacySoftwareAlgorithms

Substanzen

Proteins

Autor:innen und Institutionen

  • Department of Computer Science, University of Maryland, College Park, MD 20742, United States.
  • Center of Bioinformatics and Computational Biology, College Park, MD 20740, United States.
  • Graduate School of Design, Harvard University, Boston, MA 02138, United States.
  • Sewickley Academy, Sewickley, PA 15143, United States.
  • College of Economics and Management, China Agricultural University, Beijing 100083, China.
  • Department of Biostatistics, University of Pittsburgh, Pittsburgh, PA 15261, United States.

ORCID-Profile: Yanshuo Chen, Zhengmian Hu, Wei Chen, Heng Huang

Förderung

  • NSF

Zitieren

APA

Chen, Y., Hu, Z., Wu, Y., Chen, R., Jin, Y., Zhan, M., Xie, C., Chen, W., & Huang, H. (2025). Enhancing privacy in biosecurity with watermarked protein design. Bioinformatics. https://doi.org/10.1093/bioinformatics/btaf141

Vancouver

Chen Y, Hu Z, Wu Y, Chen R, Jin Y, Zhan M, et al. Enhancing privacy in biosecurity with watermarked protein design. Bioinformatics. 2025. doi:10.1093/bioinformatics/btaf141

BibTeX
@article{Chen2025,
  author = {Chen, Yanshuo and Hu, Zhengmian and Wu, Yihan and Chen, Ruibo and Jin, Yongrui and Zhan, Marcus and Xie, Chengjin and Chen, Wei and Huang, Heng},
  title = {Enhancing privacy in biosecurity with watermarked protein design},
  journal = {Bioinformatics},
  year = {2025},
  doi = {10.1093/bioinformatics/btaf141}
}
Kostenlos starten →