The AI-Designed Bioweapon Arms Race

Interesting article about the arms race between AI systems that invent/design new biological pathogens, and AI systems that detect them before they’re created:

The team started with a basic test: use AI tools to design variants of the toxin ricin, then test them against the software that is used to screen DNA orders. The results of the test suggested there was a risk of dangerous protein variants slipping past existing screening software, so the situation was treated like the equivalent of a zero-day vulnerability.

[…]

Details of that original test are being made available today as part of a much larger analysis that extends the approach to a large range of toxic proteins. Starting with 72 toxins, the researchers used three open source AI packages to generate a total of about 75,000 potential protein variants.

And this is where things get a little complicated. Many of the AI-designed protein variants are going to end up being non-functional, either subtly or catastrophically failing to fold up into the correct configuration to create an active toxin.

[…]

In any case, DNA sequences encoding all 75,000 designs were fed into the software that screens DNA orders for potential threats. One thing that was very clear is that there were huge variations in the ability of the four screening programs to flag these variant designs as threatening. Two of them seemed to do a pretty good job, one was mixed, and another let most of them through. Three of the software packages were updated in response to this performance, which significantly improved their ability to pick out variants.

There was also a clear trend in all four screening packages: The closer the variant was to the original structurally, the more likely the package (both before and after the patches) was to be able to flag it as a threat. In all cases, there was also a cluster of variant designs that were unlikely to fold into a similar structure, and these generally weren’t flagged as threats.

The research is all preliminary, and there are a lot of ways in which the experiment diverges from reality. But I am not optimistic about this particular arms race. I think that the ability of AI systems to create something deadly will advance faster than the ability of AI systems to detect its components.

Posted on October 30, 2025 at 7:05 AM5 Comments

Comments

Clive Robinson October 30, 2025 2:42 PM

@ Bruce, ALL,

With regards,

“I think that the ability of AI systems to create something deadly will advance faster than the ability of AI systems to detect its components.”

With out a doubt.

But there are several hidden variables to consider. Just some of which are,

“Deadly to what?”
“Deadly in what quantity?”
“Deadly by what route?”

Not all spiecies respond the same way.

Take “Cholecalciferol”(vitamin D3) even in quite large doses it’s safe for humans to consume and in the northern hemisphere some countries fortify foods with it. However rodents can be killed with it. It’s why it’s been tested for use in homes with children and pets as a safe rodenticide.

Another rodenticide will kill both rats and humans at even moderate doses (Look up the LD50). But it is one of the most important blood thiners for people with heart disease.

Most drugs are actually poisons in sufficient quantities which is why Drs “titrate” people onto a drug when they first start using it.

But even many foods are poisons. Take chocolate, the lethal dose in humans is something like 10kg. But your pet dog can be killed with just a couple of squares from a chocolate bar. And why vets dred both Xmas and Easter as they know heartbreak is going to cross their threshold.

In the US a chemical used as a strong laxative is put in pancake syrup. Likewise a form of sugar called Fructose which is also bad for the liver.

Even ordinary cabbage can kill people as it has significant effect on warfrin.

Did you know that most fruit pits contain cyanide as do quite a number of other plants. Which means that there are ways they have to be prepared.

Red kidney beans, cassava/yuca and several others vegetable foods will kill you. With some like ruhbarb and potatoes it’s the green roots and leaves with others it’s the tubers. And others like tomatoes it’s all but the fruit. Other plants like the seemingly everlasting weed “Jerusalem Artichokes” contain things like inulin, that can be really bad for your guts if you don’t cook them.

As for proteins as poisons, like most proteins they generally depolarise and become useless / non lethal simply by cooking in boiling water for around ten minutes (why kidney and other pulses should have warnings on the packets).

The two classic example of proteins changing are eggs when you boil them and milk forming a natural plastic “casin” when heated up with an acids like vinegar something we also call cheese.

I won’t go through “by what route” but injection, ingestion, and inhalation are three of several different routes into the body.

We already have “alpha fold” finding viable proteins but we can’t screen even a fraction of them because we’ve not found a way to determine what they might do, in any given species, let alone predict which will be poisonous.

And this is where we crash into the major problem with Current AI LLM and ML Systems. That is even within narrow bounds of the “known” they can not really tell us very much.

ResearcherZero October 31, 2025 3:25 AM

@Clive Robinson

The mosquito or tick to arm or leg route. 😉

The unfortunate nature of zoonotic diseases is that they are not just confined to the human genome. A biological weapon could potentially jump species, allowing it to survive outside of human populations. The current changes in climatic conditions and our own human behaviors (including the somewhat and very stupid ones) are amplifying these risks.

The summer of 2023/2024 saw the driest conditions in 150 years. An illness emerged which is blinding and paralyzing Ring-Tail Possums.

‘https://www.abc.net.au/news/2025-10-30/mystery-possum-virus/105939450

Another virus Lorikeet Paralysis Syndrome (LPS), is killing flying foxes and lorikeets.
https://au.news.yahoo.com/race-to-find-cause-of-mystery-illness-killing-two-native-aussie-species-numbers-are-staggering-023046743.html

The H5N1 strain has killed hundreds of seal pups on Heard Island 4000 km southwest of Perth, Western Australia. Australia has done very little to prepare for potential mass mortality events in Australian bird populations and other wildlife, or protect their natural habitat from destruction. The funding of environmental protection and staffing levels to carry it out have declined – while the risks to the environment have increased.

While H5N1 may not become a pandemic amongst humans, it would potentially decimate Australian native species, weaken their resilience and could lead to the extinction of some species. By reducing numbers of important species, it could also lead to increased spread of other diseases. Likewise, such diseases could kill large numbers of farm animals.

The loss of birds and bats that predate on insects would aid in this. The low genetic diversity within the dense animal populations of industrialized farming is perfect breeding ground for infectious diseases From the infected species it is then possible for some mosquito-born viruses or other transmissible diseases to move through human populations.

https://connectsci.au/ma/article/45/1/32/74234/Emerging-viral-threats-in-Australia

Many of viruses that affect animals, birds or reptiles can be spread by ticks or mosquitoes where they are far harder to control.
https://www.mdpi.com/1999-4915/13/10/2099

Clive Robinson October 31, 2025 6:15 AM

@ Researcher Zero,

What I’m going to say is going to sound brutal and worse, but it is unfortunately the view those creating the problem appear to have.

You outline the problem as,

“Australia has done very little to prepare for potential mass mortality events in Australian bird populations and other wildlife, or protect their natural habitat from destruction. The funding of environmental protection and staffing levels to carry it out have declined – while the risks to the environment have increased.”

The viewpoint that has caused this is,

“Australia is a mostly useless waste land and all it has of worth is minerals and sunshine”.

The result the political power that money attracts and vise versa has resulted in Australian Politicians kissing the brown ring of the worst of Capitalism’s Exploiters and decimaters.

I must stress that the viewpoint is not mine (I happen to like Aus for most of it’s charms, though I’m now a little to old to enjoy many of them, I nearly emigrated half a lifetime ago…).

But an examination of political and industrial activity leads to the conclusion that is the viewpoint that matters to those in power and politics.

lurker October 31, 2025 7:05 PM

@ResearcherZero
re mystery possum virus

A deadly virus specific to brush-tailed possum, natural or AI assisted, would be very welcome on this side mate.

Leave a comment

Blog moderation policy

Login

Allowed HTML <a href="URL"> • <em> <cite> <i> • <strong> <b> • <sub> <sup> • <ul> <ol> <li> • <blockquote> <pre> Markdown Extra syntax via https://michelf.ca/projects/php-markdown/extra/

Sidebar photo of Bruce Schneier by Joe MacInnis.