Mostly Tilting at Windmills, a six-part series that points machine learning techniques at Bitcoin nonce prediction and measures how each one fails. The remainder is Keycarver, which carves lost Bitcoin keys out of old USB drives.
Recent
Tilting at Windmills VI
A pre-registered Gohr-style distinguisher pointed at the carry wall: the network beats the hand-built score where signal exists, and finds nothing one round deeper.
Tilting at Windmills V
Carry depth as the structural measure of mining hardness: SHA-256d puts 386 adder layers between the header and the output, and the strongest local advantage we can measure falls off a cliff within a single round.
Tilting at Windmills IV
Six pre-registered feature families and 810 stem buckets, all null: the remaining attack surfaces on SHA-256d mining, enumerated and closed, leaving brute force unbeatable short of a SHA-256 break.
Tilting at Windmills III
A hand-computed carry score selects nonces 67% better than random at any depth inside one SHA-256 block, a closed form predicts it to half a percentage point, and the second hash pays nothing for any of it.
Tilting at Windmills II
A Decision Transformer, three loss functions, a SAT solver, a game tree, an arbitrary-precision probe, and a brute-force oracle, pointed at nonce prediction in turn. The hash holds; the question improves.
Keycarver
I had a junk drawer of old USB drives and a suspicion that some lost Bitcoin keys were still on them. The keys were there. The wallets were empty.
Tilting at Windmills I
REINFORCE applied to nonce prediction, and why SHA-256's avalanche effect makes the expected gradient exactly zero.