← Back to context

Comment by upofadown

2 hours ago

My article:

2048 Bit RSA and the Year 2030 https://articles.59.ca/doku.php?id=em:20482030

We don't have any way to predict when and if 2048 bit RSA would be factorable at this time. We would need a breakthrough in hardware and/or algorithms. The common estimation that it is equivalent to the difficulty of brute forcing symmetrical 112 bit encryption seems to be based on some sort of straightforward extrapolation. It doesn't take into account the amount of memory required for the poorly reducible matrix reduction step in the currently known best algorithm. That's 10^18 bytes of memory, or a million terabytes, somehow coupled to enough processing power to actually make anything possible.

Even if you accept the 112 bit estimate, that works out to something like 400 thousand years using the Bitcoin network as a reference to what we could reasonably achieve.