AI designs for dangerous DNA can slip past biosecurity measures, study shows

A new study found that artificial intelligence could design DNA for all kinds of dangerous proteins, and do it in such a way that DNA manufacturers’ biosecurity screening measures would not reliably catch them. Malte Mueller/fStoap/Getty Images

Malte Mueller/fStoap/Getty Images

Major biotech companies that churn out made-to-order DNA for scientists have protections in place to keep dangerous biological material out of the hands of would-be evil-doers. They screen their orders to catch anyone trying to buy, say, smallpox or anthrax genes.

But now, a new study in the journal Science has demonstrated how AI could be used to easily circumvent

→ Continue reading at NPR - Technology

More from author

Related posts

Advertisment

Latest posts

AI-designed proteins test biosecurity safeguards

New patches to biosecurity screening software can make it harder to produce potentially harmful proteins using artificial intelligence. Around the world, this software monitors...

Elizabeth Warren calls for Trump to release the jobs report despite shutdown | CNN Business

Democratic Sen. Elizabeth Warren is calling on the Trump administration to release the September jobs report on Friday despite the ongoing government shutdown,...

How dandelions rig the odds for catching upward gusts

It’s surprisingly difficult — by puffing from any one direction — to send all of a dandelion’s delicate white seed tufts wafting away from...