Thanks for drawing this line between biorisk and AI risk.
Somewhat related: I often draw parallels between threat models in cyber security and certain biosecurity questions such as DNA synthesis screening. After reading your write-up, these two seem much closer related than biorisk and AI risk and I’d say cyber security is often a helpful analogy for biosecurity in certain contexts. Sometimes biosecurity intersects directly with cyber security, that is when critical information is stored digitally (like DNA sequences of concern). Would be interested in your opinion.
I think there are useful analogies between specific aspects of bio, cyber, and AI risks, and it’s certainly the case that when the biorisk is based on information security, it’s very similar to cybersecurity, not the least in that it requires cybersecurity! And the same is true for AI risk; to the extent that there is a risk of model weights leaking, this is in part a cybersecurity issue.
So yes, I certainly agree that many of the dissimilarities with AI are not present if analogizing to cyber. However, more generally, I’m not sure cybersecurity is a good analogy for biorisk, and have heard that computer security people often dislike the comparison of computer viruses and biological viruses for that reason, though they certainly share some features.
Thanks for drawing this line between biorisk and AI risk.
Somewhat related: I often draw parallels between threat models in cyber security and certain biosecurity questions such as DNA synthesis screening. After reading your write-up, these two seem much closer related than biorisk and AI risk and I’d say cyber security is often a helpful analogy for biosecurity in certain contexts. Sometimes biosecurity intersects directly with cyber security, that is when critical information is stored digitally (like DNA sequences of concern). Would be interested in your opinion.
I think there are useful analogies between specific aspects of bio, cyber, and AI risks, and it’s certainly the case that when the biorisk is based on information security, it’s very similar to cybersecurity, not the least in that it requires cybersecurity! And the same is true for AI risk; to the extent that there is a risk of model weights leaking, this is in part a cybersecurity issue.
So yes, I certainly agree that many of the dissimilarities with AI are not present if analogizing to cyber. However, more generally, I’m not sure cybersecurity is a good analogy for biorisk, and have heard that computer security people often dislike the comparison of computer viruses and biological viruses for that reason, though they certainly share some features.