-----BEGIN PGP SIGNED MESSAGE----- In article <199511111800.NAA23831@jekyll.piermont.com>, Perry E. Metzger <perry@piermont.com> wrote:
Perhaps neural nets could be used in an unknown plain text, brute force attack to automatically select possible decryptions for human examination. I don't know of any papers on the subject.
I remember seeing a good paper by our own David Wagner on how to do this without anything more than some ordinary statistics -- no complicated junk required. David, if you are reading this, could you comment?
Check out http://www.cs.berkeley.edu/~daw/recog.ps for a paper by Steve Bellovin & me on doing plaintext recognition with ordinary statistics. It has nothing to do with neural networks, though.... - --- [This message has been signed by an auto-signing service. A valid signature means only that it has been received at the address corresponding to the signature and forwarded.] -----BEGIN PGP SIGNATURE----- Version: 2.6.2 Comment: Gratis auto-signing service iQBFAwUBMKZvoCoZzwIn1bdtAQHItQGA1jD4SjC1Vg1fwCO3VLJ7v+gUlUvncwhj v2SwPURAjry2QAeWBNeL5hMJARQuQHNx =Cepa -----END PGP SIGNATURE-----