From: daw@delhi.CS.Berkeley.EDU (David A Wagner)
Date: Tue, 14 Nov 1995 20:28:26 +0800
To: cypherpunks@toad.com
Subject: Re: coding and nnet's
Message-ID: <199511122205.RAA24984@bb.hks.net>
MIME-Version: 1.0
Content-Type: text/plain


-----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-----