diff --git a/packages/shade-crypto-web/tests/hardening.test.ts b/packages/shade-crypto-web/tests/hardening.test.ts index 584f342..c308a4c 100644 --- a/packages/shade-crypto-web/tests/hardening.test.ts +++ b/packages/shade-crypto-web/tests/hardening.test.ts @@ -59,26 +59,40 @@ describe('Cryptographic Hardening', () => { const mismatchAtEnd = new Uint8Array(target); mismatchAtEnd[len - 1] ^= 0xff; - // Measure many iterations to get a stable signal - const iterations = 50000; + const iterations = 20000; + const measure = (other: Uint8Array): number => { + const t0 = performance.now(); + for (let i = 0; i < iterations; i++) crypto.constantTimeEqual(target, other); + return performance.now() - t0; + }; - const start1 = performance.now(); - for (let i = 0; i < iterations; i++) { - crypto.constantTimeEqual(target, mismatchAtStart); + // Warm up before measuring anything. The first loop through this code + // pays for JIT compilation that the second one does not, which biased + // whichever side ran first and is why the old version had to "allow 2x + // for JIT/noise" — a tolerance covering a measurement artefact rather + // than the property under test. + measure(mismatchAtStart); + measure(mismatchAtEnd); + + // Paired, interleaved samples, compared by median. A single pair is one + // GC pause away from a false alarm: this test failed roughly one run in + // fourteen on a loaded machine on 08.09.2026, and a security test that + // cries wolf under load is a security test people learn to re-run until + // it passes. The median throws out the pause instead of the property. + const ratios: number[] = []; + for (let round = 0; round < 5; round++) { + const a = measure(mismatchAtStart); + const b = measure(mismatchAtEnd); + ratios.push(Math.max(a, b) / Math.min(a, b)); } - const timeStart = performance.now() - start1; + ratios.sort((x, y) => x - y); + const median = ratios[Math.floor(ratios.length / 2)]!; - const start2 = performance.now(); - for (let i = 0; i < iterations; i++) { - crypto.constantTimeEqual(target, mismatchAtEnd); - } - const timeEnd = performance.now() - start2; - - // With constant-time comparison, these should be very close. - // Non-constant-time would show timeEnd >> timeStart (early exit vs full scan). - // Allow 2x variance for JIT/noise, but it should never be 10x. - const ratio = Math.max(timeStart, timeEnd) / Math.min(timeStart, timeEnd); - expect(ratio).toBeLessThan(3); + // The threshold is unchanged and deliberately so: an early-exit compare + // would take ~256x longer to reach a mismatch in the last byte than the + // first, on every single round. Nothing about sampling weakens what this + // catches — it only stops the scheduler from answering for the code. + expect(median).toBeLessThan(3); }); });