
"It details how protein-design strategies aided by artificial intelligence (AI) could circumvent the screening software that many DNA-synthesis firms use to ensure that they avoid unintentionally producing sequences encoding harmful proteins or pathogens. The researchers used an approach from the cybersecurity world: 'red teaming', in which one team attempts to break through another's defences (with their knowledge)."
"They found that some screening tools were unprepared to catch AI-generated protein sequences that recreate the structure, but not the sequence, of known biothreats, says Eric Horvitz, chief scientific officer at Microsoft in Redmond, Washington. This is a type of zero-day vulnerability - one that, in the cybersecurity world, blindsides software developers and users. "The diversified proteins essentially flew through the screening techniques" that were tested, Horvitz says."
"After the developers patched their software to address the new threat, the tools performed much better, flagging all but about 3% of malicious sequences in a larger second attempt. The impetus for the study is researchers' rapidly growing ability to create new, custom proteins. Armed with AI-powered tools such as RFdiffusion and ProteinMPNN, researchers can now invent proteins to attack tumours, defend against viruses and break down -pollutants."
AI-enabled protein-design methods can generate sequences that reproduce protein structures without sharing sequence similarity to known threats, enabling evasion of sequence-based biosecurity screens. Red-teaming exercises using cybersecurity attack simulations revealed that many existing DNA-synthesis screening tools initially failed to detect such diversified designs. After targeted software patches, detection rates improved markedly, though a small fraction of malicious sequences (about 3%) still slipped through in later tests. Widely used design platforms such as RFdiffusion and ProteinMPNN accelerate creation of novel proteins for therapeutics and environmental applications while also posing potential misuse risks.
Read at Nature
Unable to calculate read time
Collection
[
|
...
]