At 7:52 PM 11/10/95, Bill Stewart wrote:
Schneier's 2nd edition says "Neural nets aren't terribly useful for cryptography, primarily because of the shape of the solution space. Neural nets work best for problems that have a continuity of solutions, some better than others. This allows a neural net to learn, proposing better and better solutions as it does. Breaking an algorithm provides for very little in the way of learning opportunities: You either recover the key or you don't. (At least this is true if the algorithm is any good.) Neural nets work well in structured environments when there is something to learn, but not in the high-entropy, seemingly random world of cryptography." And he doesn't give any references. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
This paragraph sounds a _lot_ like what I wrote in sci.crypt a while back on the usefullness of AI and neural nets for crypto. Sounds almost like exactly the paragraph I wrote, in fact. And I recollect that Bruce dropped me a note saying I made the point succinctly and that he wanted to use what I said in his next edition. (My recollection at least, but I don't have any easy way anymore of searching my several hundred megs of accumulated mail, articles, etc.) I have no problem with Bruce using my points. I hope he didn't use my _exact_ words, though. But not a cosmic issue. --Tim May Views here are not the views of my Internet Service Provider or Government. ---------:---------:---------:---------:---------:---------:---------:---- Timothy C. May | Crypto Anarchy: encryption, digital money, tcmay@got.net 408-728-0152 | anonymous networks, digital pseudonyms, zero Corralitos, CA | knowledge, reputations, information markets, Higher Power: 2^756839 | black markets, collapse of governments. "National borders are just speed bumps on the information superhighway."