New Delhi: Microsoft researchers used AI to discover a zero-day vulnerability in the biosecurity screening software. This software is designed to prevent the misuse of to create deadly toxins or pathogens. The discovery, which was led by Microsoft’s chief scientists, shows how the AI can bypass biosecurity defenders. Some sources stated that researchers focused on generative AI algorithms, the same types of programs that fuel drug discovery at major startups. This software has dual-use potential to generate both beneficial and harmful molecules.
Microsoft initiated a red teaming test in 2023 to assess whether adversarial AI protein design could aid bioterrorists in manufacturing hazardous proteins. To execute the attack, Microsoft used several generative protein models to redesign known toxins subtly. This manipulation was predicted to preserve the deadly function while allowing the DNA sequence to bypass the biosecurity screening software used by commercial vendors. Microsoft confirmed that the exercise was entirely digital and that no toxic proteins were ever produced.
The company alerted the US government and software makers, who have since patched their systems. To prevent misuse of the research, Microsoft did not disclose some of its code or reveal which toxic proteins the AI was tasked with redesigning. Some expected doubt that focusing solely on commercial synthesis is the best defence.
