Dangerous AI-Designed Proteins Could Evade Today’s Biosecurity Software
In a ‘red teaming’ effort led by Microsoft researchers, biosecurity programs struggled to flag AI-generated toxins.
The post Dangerous AI-Designed Proteins Could Evade Today’s Biosecurity Software appeared first on SingularityHub.
Link :
https://singularityhub.com/2025/10/06/dangerous-ai-designed-proteins-could-evade-todays-biosecurity-software/