AI Can Design Dangerous DNA That Evades Security, Study Finds
Research published in the journal 'Science' showed AI can "paraphrase" DNA codes for toxins, bypassing existing biosecurity screening measures.
A New Biosecurity Risk
A new study published in the journal Science on Oct. 2, 2025, revealed that artificial intelligence can be used to design DNA for dangerous proteins in ways that are not reliably caught by existing biosecurity screening measures. The research highlights a significant and growing security risk at the intersection of AI and biotechnology.
The study was conducted by a team of AI researchers, including Microsoft's chief scientific officer, Eric Horvitz. The team used an AI program to "paraphrase" the DNA codes of toxic proteins, re-writing them in ways that could preserve their function while evading …
Archive Access
This article is older than 24 hours. Create a free account to access our 7-day archive.