PoCoFL: POlicy-COmpliant Federated Learning
PoCoFL uses commitments and non-interactive zero-knowledge proofs to verify policy-compliant client contributions and correct aggregation in federated learning.
6 stories, newest first · one card per story
PoCoFL uses commitments and non-interactive zero-knowledge proofs to verify policy-compliant client contributions and correct aggregation in federated learning.
Locus framework automates ASIC and FPGA point-addition designs for elliptic curves, achieving 2.71x speedups and 3.11x area reductions for ZKPs.
ZEBRA verifies zkVM constraint systems via branch-and-bound cardinality counting, finding 11 zero-day bugs across five real-world zkVMs and running 51.5x faster than SMT verification.

Fields Medalist Jacob Tsimerman founds the Mathematical AI Safety Institute (MAISI) to pursue provable AI safety guarantees, launching January 2027.
Atlas delivers zero-knowledge proofs for HNSW semantic search, verifying RAG retrieval in under a second on SIFT1M and 2.0 seconds at 100M vectors.
Guppy lets blockchain light clients verify full state via recursive zero-knowledge proofs without validators maintaining state commitments, processing thousands of updates per second.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views