 Laan Tungir
|
b1f8076b1d
|
v0.1.5 - Fixed ml-dsa-65 SHAKE re-squeeze domain separation bug: poly_challenge, poly_eta, and poly_uniform_gamma1 re-absorbed the same seed on buffer exhaustion, producing identical output and potentially hanging the SampleInBall rejection loop; added a monotonic re-squeeze counter to the absorb buffer so each re-squeeze produces fresh bytes; note: ml-dsa-65 sign still hangs because the rejection loop never accepts a candidate — this is a separate NTT-correctness bug in the matvec/scalar multiplication wrappers that requires comparison against a PQClean reference implementation
|
2026-07-27 19:07:51 -04:00 |
|