ENDAR AI system detects bioweapons by analyzing DNA patterns

A new AI-powered detection system called ENDAR can identify artificially engineered genetic material by analyzing DNA patterns, potentially solving the long-standing problem of determining whether disease outbreaks are natural or human-made. Developed by Ginkgo Bioworks, a synthetic biology company, with support from US intelligence agencies, this technology could be crucial as artificial intelligence makes bioweapons easier to create and deploy.

The big picture: The convergence of AI and synthetic biology is creating unprecedented opportunities for both beneficial medical advances and dangerous bioweapons development.

• AI tools can now help design entirely new pathogens or modify existing ones to be more deadly, transmissible, or resistant to treatments.
• A 2023 MIT experiment showed that commercially available AI chatbots could provide step-by-step instructions for assembling deadly viruses like smallpox.
• Experts warn that AI could enable the creation of pathogens with “the death rate of Ebola but the transmissibility of seasonal flu,” potentially causing billions of deaths.

Why this matters: Unlike nuclear weapons, bioweapons are nearly impossible to detect before use and can provide plausible deniability to attackers.

• The 1979 Soviet anthrax accident in Sverdlovsk killed over 60 people but remained secret for decades because biological weapons facilities look identical to legitimate medical labs.
• Current uncertainty about COVID-19’s origins demonstrates how difficult attribution can be even with extensive investigation.
• As Stanford’s Drew Endy, a professor of biological engineering, notes: “What the pandemic tells us is that nobody can do attribution.”

How ENDAR works: The system uses machine learning trained on vast libraries of engineered genomes to detect genetic anomalies that indicate artificial manipulation.

• It analyzes DNA at the base pair level, looking for patterns that don’t match natural evolutionary history.
• The technology can “calculate a molecular clock and say, ‘Does its ancestry match what we would expect, given the evolutionary history?'”
• If patterns don’t align with natural evolution, this signals potential genetic engineering.

Current monitoring efforts: Ginkgo Bioworks operates surveillance systems at eight US airports plus international locations, collecting samples from passengers and aircraft wastewater.

• The company processes samples through polymerase chain reaction (PCR) testing to identify genetic material.
• This creates a global database of pathogen movement and evolution patterns.
• The same infrastructure used for COVID-19 monitoring has been adapted for bioweapons detection.

The threat landscape: Several nations are believed to maintain active biological weapons programs despite international treaties prohibiting them.

• The State Department assesses that Russia and North Korea maintain offensive bioweapons programs.
• China has “continued to engage in biological activities with potential [bioweapon] applications” according to US intelligence.
• Chinese military writings have identified biotechnology as a “new domain of warfare.”

Information warfare concerns: AI could amplify bioweapons threats through sophisticated misinformation campaigns.

• Epidemiologist Jay Varma warns of “a rogue actor using existing AI tools to simulate a bioterrorism attack that would destabilize a region or the world.”
• False evidence of biological attacks spread on social media could trigger security crises between nuclear powers.
• Russia has already spread unsubstantiated claims about Ukrainian bioweapons labs.

What experts are saying: The focus should be on building resilience rather than pursuing deterrence through offensive capabilities.

• “We don’t want to go down the deterrence path,” says Stanford’s Endy. “We want to go down the resilience path.”
• Ginkgo’s Matt McKnight, head of biosecurity at the company, argues: “You can’t regulate your way out of it. You have to be better at it. You have to be as good as the adversaries at making countermeasures.”
• MIT’s Kevin Esvelt, director of the Sculpting Evolution group, warns that synthetic biology “just seems to favor offense” because “it’s much cheaper to build a virus than it is to develop and distribute a vaccine.”

Looking ahead: The technology arms race between offensive and defensive biological capabilities is accelerating, with detection systems like ENDAR representing a crucial defensive breakthrough in an increasingly dangerous landscape.