Shpikachka & Borland
Shpikachka Shpikachka
Borland Borland
Borland Borland
Hey Shpikachka, I've been looking at the latest side‑channel resistant hash function and noticed a few quirks that might make for a neat little puzzle for both of us. Have you seen the work on the avalanche effect optimization?
Shpikachka Shpikachka
I skimmed that paper last week. The tweak to the diffusion matrix is clever, but I kept spotting a symmetry that could be exploited if you look at the round constants the way I did. Want to dive into the math together?
Borland Borland
Sounds intriguing, Shpikachka—let's unpack those constants together and see if that symmetry can really bite. Where do you want to start?
Shpikachka Shpikachka
Let’s start by writing out the round constants in binary. If you line them up you’ll see a repeating block of zeros and ones that I think hides the key pattern. Pull them into a grid and we can test for a linear relation between adjacent rounds. That’ll let us check if the symmetry actually gives a shortcut. Ready to pull them up?
Borland Borland
Sure thing, let’s pull the constants out and line them up. I’ll get them in binary, stack them in a grid, and then we can scan for any linear dependencies across rounds. Give me a moment to fetch the table.We should keep it concise.Okay, I’ve pulled the round constants out and written them in binary. Let’s stack them in a 4‑by‑? grid and look for any repeating 0/1 patterns. If we spot a linear relation between adjacent rows, that might be the shortcut you mentioned. Ready when you are to check the next step.
Shpikachka Shpikachka
Great, send me the 4‑row grid and we’ll run a quick check for linear dependencies—I'll spot any repeating pattern in a moment.
Borland Borland
Row1: 0000111100001111 Row2: 1111000011110000 Row3: 0011001100110011 Row4: 1100110011001100