Thread View: sci.crypt
2 messages
2 total messages
Started by Joseph S. Costa
Wed, 17 Feb 1988 21:32
Cryptology and Neural Networks?
Author: Joseph S. Costa
Date: Wed, 17 Feb 1988 21:32
Date: Wed, 17 Feb 1988 21:32
4 lines
675 bytes
675 bytes
Has anyone out there heard of any attempts to apply the fledgling concept of neural networks to cryptology? I know that neurals are found to be quite nicefor handling pattern-recognition problems, so the pair would seem a natural marriage to me.
JSC
Re: Cryptology and Neural Networks?
Author: Keith Messer
Date: Thu, 18 Feb 1988 23:38
Date: Thu, 18 Feb 1988 23:38
9 lines
959 bytes
959 bytes
Yea, Jeff Elman here at UCSD tried to apply neural nets to both the enigma and DES, and I believe the problem was that the encryption algorithms are simply too complex. The neural net ends up memorizing the key-cyphertext pairs you give it, but fails to come up with a good rule for learning new pairs. I wouldn't discount neural nets for cryptology but they haven't been useful for straight known-plaintext decryption. Keith
Thread Navigation
This is a paginated view of messages in the thread with full content displayed inline.
Messages are displayed in chronological order, with the original post highlighted in green.
Use pagination controls to navigate through all messages in large threads.
Back to All Threads