When AIs Start Hacking

2021-04-26 11:06

To date, hacking has exclusively been a human activity.

Separately, AIs can engage in something called reward hacking.

How realistic is AI hacking in the real world? The feasibility of an AI inventing a new hack depends a lot on the specific system being modeled.

For an AI to even start on optimizing a problem, let alone hacking a completely novel solution, all of the rules of the environment must be formalized in a way the computer can understand.

These are artificial and constrained, with all of the rules specified to the AI. The inherent ambiguity in most other systems ends up being a near-term security defense against AI hacking.

This is all something we need to figure out now, before these AIs come online and start hacking our world.

News URL

https://www.schneier.com/blog/archives/2021/04/when-ais-start-hacking.html

#AI #hacking