Talk:Neural cryptography

Untitled
Sorry, but I removed the part "Security against quantum computers". It seems to me that this is a very important fact to let it in the article without proper references. —Preceding unsigned comment added by Faturita (talk • contribs) 05:36, 27 November 2008 (UTC)


 * I restored it, and added a reference. Alas, my reference says that the original algorithm is not secure. --68.0.124.33 (talk) 20:25, 8 December 2008 (UTC)

External links modified (February 2018)
Hello fellow Wikipedians,

I have just modified one external link on Neural cryptography. Please take a moment to review my edit. If you have any questions, or need the bot to ignore the links, or the page altogether, please visit this simple FaQ for additional information. I made the following changes:
 * Added archive https://web.archive.org/web/20070712012959/http://www.scipub.org/fulltext/jcs/jcs29710-715.pdf to http://www.scipub.org/fulltext/jcs/jcs29710-715.pdf

When you have finished reviewing my changes, you may follow the instructions on the template below to fix any issues with the URLs.

Cheers.— InternetArchiveBot  (Report bug) 13:32, 16 February 2018 (UTC)

Protocol Details 2.4.2
In 2.4.2:


 * "Outputs are different: one of the suitable learning rules is applied to the weights"

Do both parties update their models? Which output do they use? The "Learning with own tree parity machine" section says:
 * "Output(A) = Output(B) = Output(E): All the three parties update weights in their tree parity machines."

which contradicts parts 2.4.1 and 2.4.2 of the protocol.

Update: The paper seems to indicate that the protocol is wrong. . I'll update the protocol.