ML-DSA·Digital signature·NIST level 3

ML-DSA-65

ML-DSA (FIPS 204) is a lattice-based digital signature scheme, standardized by NIST in August 2024. Built on Module Learning With Errors, it offers fast verification and moderate signature sizes.

Latest run2026-09-21 11:47 UTC

commit6ed429a

CPU: Xeon Platinum 8488C
Measured on: c7i.large
OS / Kernel: 24.04.4 LTS
liboqs: 0.15.0
Wall clock: 32m 32s
CPU steal: <0.01%

Parameters

Family: ML-DSA
Parameter set: 65
Public key: 1.91 KB
Private key: 3.94 KB
Signature: 3.23 KB
Iterations / op: 1,000
liboqs key: ML-DSA-65

Regulatory approval status

Whether this algorithm family is approved/recommended for use under three regimes. Every badge links to its source — click through before citing this elsewhere.

CNSA 2.0 (US/NSA)Approved

CNSA 2.0 replaces ECDSA/RSA digital signatures with ML-DSA.

NSA CNSA 2.0 Cybersecurity Advisory · not directly verified this session, spot-check the source

BSI TR-02102-1 (DE)Recommended

Covered under §5.3.4 "Quantum-Safe Signature Schemes" (current 2026-01 version).

BSI TR-02102-1, Version 2026-01 · not directly verified this session, spot-check the source

ANSSI (FR)Conditional

Same recommendation pattern as ML-KEM: highest available NIST level (5 preferred, else 3), standardized parameters only.

ANSSI views on the Post-Quantum Cryptography transition (2023 follow up), §2

keygenGenerate a fresh key pair.

131 of 131 runs

Mean: 30.3 µs
95% CI on mean: ±1.01%
Median: 28.7 µs
p95: 39.8 µs
p99: 49.0 µs
Stdev: 5.0 µs
Min: 27.6 µs
Ops/sec: 33,000

Mean is known to 30.00–30.61 µs across 1,000 iterations. A 95% confidence interval on the mean, not a prediction interval for a single operation. It says how precisely the average is known from this run's samples; the standard deviation says how much the individual samples scattered.

Mean over time

Click any point to view the GitHub Actions run that produced it.

signProduce a signature over a message using the private key.

131 of 131 runs

Mean: 129.3 µs
95% CI on mean: ±3.74%
Median: 107.3 µs
p95: 277.9 µs
p99: 413.6 µs
Stdev: 78.1 µs
Min: 39.0 µs
Ops/sec: 7,732

Mean is known to 124.49–134.17 µs across 1,000 iterations. A 95% confidence interval on the mean, not a prediction interval for a single operation. It says how precisely the average is known from this run's samples; the standard deviation says how much the individual samples scattered.

Mean over time

Click any point to view the GitHub Actions run that produced it.

verifyVerify a signature against a message and public key.

131 of 131 runs

Mean: 29.8 µs
95% CI on mean: ±0.45%
Median: 29.4 µs
p95: 34.3 µs
p99: 39.3 µs
Stdev: 2.2 µs
Min: 28.1 µs
Ops/sec: 33,506

Mean is known to 29.71–29.98 µs across 1,000 iterations. A 95% confidence interval on the mean, not a prediction interval for a single operation. It says how precisely the average is known from this run's samples; the standard deviation says how much the individual samples scattered.

Mean over time

Click any point to view the GitHub Actions run that produced it.