@agreeable_landfall@mastodon.social
Post #4177962
2026-07-28 23:16 UTC
@SteveBellovin@infosec.exchange @cryptomancer @CryptoOrrDun@ioc.exchange An LLM might find _something_, but I won't believe it's a crack until a cryptographer or two with deep experience says it's a crack.
Replies (1)
-
@SteveBellovin@infosec.exchange 2026-07-29 00:36
@agreeable_landfall@mastodon.social @cryptomancer @CryptoOrrDun@ioc.exchange What concerns me is a Kobayashi Maru sort of scenario, where instead of finding a crack in an algorithm the LLM hacks the researchers' accounts and steals the file with the secret key or the plaintext, all unknown to the researchers.