"Those gaping security holes and how they were discovered were kept confidential until Thursday, when a report in the journal Science detailedhow researchersgeneratedthousands of AI-engineered versions of 72 toxins that escaped detection. The research team, a group of leading industry scientists and biosecurity experts, designed a patch to fix this problem foundin four different screening methods. But they warn that experts will have to keep searching for future breaches in this safety net."
""This is like a Windows update model for the planet. We will continue to stay on it and send out patches as needed, and also define the research processes and best practices moving forward to stay ahead of the curve as best we can," Eric Horvitz, chief scientific officer of Microsoft and one of the leaders of the work, said at a press briefing."
Two Microsoft scientists discovered a serious vulnerability in a safety net meant to prevent misuse of AI for designing hazardous proteins. Details remained confidential until a report revealed researchers generated thousands of AI-engineered variants of 72 toxins that escaped detection. A multidisciplinary team produced a patch addressing the flaw across four screening methods. The team emphasized that continued adversarial searches and updates will be necessary. Researchers ran an adversarial pilot in October 2023 without manufacturing any proteins, producing only digital versions. AI protein design offers benefits but also creates dual-use biosecurity risks, and no single solution will suffice.
Read at The Washington Post
Unable to calculate read time
Collection
[
|
...
]