This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility:
Artificial intelligence is now capable not only of analyzing biological data but also of designing new DNA, RNA, and protein sequences. To lay the groundwork for responsible innovation, an international and interdisciplinary research team led by University Medical Center Mainz proposes a multi-tiered security architecture for the use of generative AI in biology. The publication was published in the journal Nature Communications.
Generative AI can design biological sequences, ranging from proteins to viral genomes. This opens up opportunities for medicine and biotechnology—for example, in the development of new drugs and therapies—but also carries the risk of misuse. An international team of researchers therefore proposes in the publication "A defense-in-depth strategy for securing AI-driven biological sequence design" that security mechanisms be integrated into AI models in biology from the very beginning.
The recommendation emerged from a three-day "sandpit" ideas workshop organized by the Wübben Stiftung Wissenschaft in November 2025, where 20 experts from the fields of molecular biology, AI, bioinformatics, ethics, medicine and politics developed strategies for using generative AI safely and responsibly. To this end, they analyzed dual-use risks of generative AI, in which technologies developed, for instance, for medical or scientific purposes could be misused.
"Such risks include, for example, new pandemics or the development of pathogens in crops," explains lead author Dr. Maximilian Sprang, a researcher at the Department of Dermatology at University Medical Center Mainz and group leader at the Institute for Quantitative and Computational Biosciences (IQCB) at Johannes Gutenberg University Mainz.
Source link







