Security

Measuring Human Cryptanalysis Effort

Read full article at source ↗

Based on a feed excerpt; full article content has not been acquired. Source evidence retrieved 15/10/2026, 16:30:23 UTC.

Briefings

Matthew Green's AI pipeline using Claude Fable 5.1 and Claude Opus 5.5 estimates cryptanalysis effort by converting published papers into research-allocation years across elliptic curves, lattices, and ECDLP. The study identifies that lattices have overtaken elliptic curves in cumulative work, though this is inferred under stated productivity assumptions. Unpublished work and secret intelligence efforts are excluded, representing a preliminary metric of public-key cryptanalysis.

Key points

• Matthew Green's AI pipeline converts published papers into estimated research-allocation years for elliptic curves, lattices, and ECDLP.
• Lattices have overtaken elliptic curves in cumulative cryptanalysis effort, though this is inferred under stated productivity assumptions.

Context and limitations

The analysis relies solely on published academic papers, excluding unpublished cryptanalysis and secret intelligence efforts. Estimates assume standard productivity rates, and the study was conducted by AI models.

Generated by Bittrees-hosted qwen35-2b sha256:aaf42c8b7c3c on 15/10/2026, 18:07:43 UTC. Based on publisher-provided feed evidence; may not cover the full original article. Check the source for details.

View archived briefing on IPFS
bafybeibxfydv6bxje3sbjhy2cqr2tmx7ogcm4sahvlpmqdc3tuwmsfdxbe