See also https://github.com/petertodd/timelock and similar projects. There might be a way to combine these two concepts plus ephemeral keys as used in perfect forward secrecy, so that the switching technology isn't a single decision to publish a key, but rather time-locking a share of a Shamir-split secret and constantly rolling it forward as the pings happen -- or letting it run out and reveal enough shares for anyone to decrypt.
I think it's really, really hard to guarantee that information has been destroyed, especially in a decentralized system, so you won't have the assurance that information was (1) available to encrypt, then (2) unavailable to anyone because it was destroyed, and then (3) somehow recovered, recalculated, or discovered to once again allow decryption. That feels isomorphic to the problem of time travel.
But maybe combining these technologies will provide a way to compartmentalize the risk of early disclosure sufficiently to satisfy some use cases.
I think it's really, really hard to guarantee that information has been destroyed, especially in a decentralized system, so you won't have the assurance that information was (1) available to encrypt, then (2) unavailable to anyone because it was destroyed, and then (3) somehow recovered, recalculated, or discovered to once again allow decryption. That feels isomorphic to the problem of time travel.
But maybe combining these technologies will provide a way to compartmentalize the risk of early disclosure sufficiently to satisfy some use cases.