Skip to content

fix(amispoof): correct analyzer/axis counts (23/18/3) + un-break opt-in mic#91

Merged
ahmetabdullahgultekin merged 1 commit into
mainfrom
fix/amispoof-counts-2026-06-01
Jun 1, 2026
Merged

fix(amispoof): correct analyzer/axis counts (23/18/3) + un-break opt-in mic#91
ahmetabdullahgultekin merged 1 commit into
mainfrom
fix/amispoof-counts-2026-06-01

Conversation

@ahmetabdullahgultekin

Copy link
Copy Markdown
Contributor

Re-applies the #89 accuracy fixes on top of #90 (which conflicted). Source-verified: 23 analyzers (20 active by default; hand + voice/audio opt-in), 18-axis liveness-proof scorer, 3 gates. Fixes the '19 analyzers / 15-axis' copy across meta/OG/Twitter/JSON-LD + README/ROADMAP, and changes microphone=() -> microphone=(self) so the opt-in 🎤 voice/audio analyzers work in prod. Supersedes #89.

…in mic

Re-applied on top of #90 (the prior #89 conflicted). Source-verified counts: 23 analyzers (20 active by default; hand + voice/audio opt-in), 18 liveness-proof axes, 3 gates. Fixed across index.html meta/OG/Twitter/JSON-LD + README/ROADMAP/web README. Also microphone=() -> microphone=(self) so the opt-in voice/audio analyzers can actually request mic permission in prod.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Copilot AI review requested due to automatic review settings June 1, 2026 09:30
@ahmetabdullahgultekin ahmetabdullahgultekin merged commit 7b87a45 into main Jun 1, 2026
@ahmetabdullahgultekin ahmetabdullahgultekin deleted the fix/amispoof-counts-2026-06-01 branch June 1, 2026 09:30

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Updates the public amispoof live-tester documentation/SEO copy to match the current source-defined analyzer/proof-axis counts, and re-enables the opt-in microphone path at the HTTP permissions layer so audio analyzers can function in production.

Changes:

  • Refresh SEO/README/roadmap copy from the stale “19 analyzers / 15-axis” wording to “23 analyzers / 18-axis” phrasing across the site and docs.
  • Update Permissions-Policy to allow same-origin microphone access (microphone=(self)) for the opt-in audio analyzers.
  • Adjust web/amispoof/README.md “What it shows” to reflect the current analyzer inventory.

Reviewed changes

Copilot reviewed 5 out of 5 changed files in this pull request and generated 8 comments.

Show a summary per file
File Description
web/amispoof/index.html Updates meta/OG/Twitter/JSON-LD copy to the new analyzer/proof-axis counts.
web/amispoof/.htaccess Enables microphone access for same-origin to support opt-in audio analyzers.
web/amispoof/README.md Updates the on-page feature summary to “23 analyzers”.
ROADMAP.md Updates the browser bundle status row with the corrected counts.
README.md Updates the project’s live-tester blurb with the corrected counts and opt-in notes.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Comment thread web/amispoof/index.html
Comment on lines 9 to 12
<meta
name="description"
content="Am I spoof? amispoof answers the question in the browser. Open face anti-spoof + liveness tester — 19 analyzers (MiniFASNet, blink, rPPG, gaze, blendshapes, 3D pose, audio-mouth sync, ...) + 15-axis passive liveness-proof scorer running entirely client-side. No server, no upload. Point your camera at a printed photo or another screen and watch the LIVE / SPOOF verdict flip in seconds."
content="Am I spoof? amispoof answers the question in the browser. Open face anti-spoof + liveness tester — 23 analyzers (20 active by default; hand & voice/audio opt-in — MiniFASNet, blink, rPPG, gaze, blendshapes, 3D pose, audio-mouth sync, ...) + 18-axis passive liveness-proof scorer running entirely client-side. No server, no upload. Point your camera at a printed photo or another screen and watch the LIVE / SPOOF verdict flip in seconds."
/>
Comment thread web/amispoof/index.html
Comment on lines 28 to 31
<meta
property="og:description"
content="Am I spoof? amispoof answers it in the browser. 19 analyzers, 3 gates, and a 15-axis passive liveness-proof scorer via onnxruntime-web + MediaPipe. Test printed-photo, phone-screen replay, deepfake, occlusion and dark-room attacks against a live LIVE/SPOOF verdict in seconds. No server, no upload."
content="Am I spoof? amispoof answers it in the browser. 23 analyzers (20 active by default; hand & voice/audio opt-in), 3 gates, and an 18-axis passive liveness-proof scorer via onnxruntime-web + MediaPipe. Test printed-photo, phone-screen replay, deepfake, occlusion and dark-room attacks against a live LIVE/SPOOF verdict in seconds. No server, no upload."
/>
Comment thread web/amispoof/index.html
Comment on lines 91 to 95
"name": "Am I spoof?",
"acceptedAnswer": {
"@type": "Answer",
"text": "amispoof answers the question in your browser in a few seconds — open https://amispoof.fivucsas.com/, grant camera access, and the page runs 19 anti-spoof analyzers + a 15-axis passive liveness-proof scorer on your face. The verdict (LIVE or SPOOF) appears in real time with per-axis evidence. Nothing is uploaded — all inference happens client-side in WebAssembly."
"text": "amispoof answers the question in your browser in a few seconds — open https://amispoof.fivucsas.com/, grant camera access, and the page runs 23 anti-spoof analyzers (20 active by default) + an 18-axis passive liveness-proof scorer on your face. The verdict (LIVE or SPOOF) appears in real time with per-axis evidence. Nothing is uploaded — all inference happens client-side in WebAssembly."
}
Comment thread README.md
- [ ] iBeta PAD-Level-1 browser-bundle submission package.

Live tester: https://amispoof.fivucsas.com/ (the old https://fivucsas.com/amispoof/ now 301s) — **19 analyzers + 3 gates + 15-axis passive liveness-proof scorer** running entirely client-side. Default-on: 17 analyzers covering the original ten plus the seven blendshape/3D-pose unlocks (eyebrow motion, blink symmetry, gaze, expression dynamics, 3D pose consistency, behavioural pattern, plus temporal + background grid brought across from `src/`). Opt-in extras: background motion (MediaPipe SelfieSegmenter), hand tracking (HandLandmarker), voice-activity + audio-mouth-sync (Web Audio API). Session recording + JSON replay shipped 2026-05-17. See `web/amispoof/README.md` for the deployment runbook and `ROADMAP.md` "Browser Port v0.1.0" for the full module inventory.
Live tester: https://amispoof.fivucsas.com/ (the old https://fivucsas.com/amispoof/ now 301s) — **23 analyzers + 3 gates + 18-axis passive liveness-proof scorer** running entirely client-side. Default-on: 20 analyzers covering the original ten plus the blendshape/3D-pose unlocks (eyebrow motion, blink symmetry, gaze, expression dynamics, 3D pose consistency, behavioural pattern), temporal + background grid brought across from `src/`, and background motion (MediaPipe SelfieSegmenter). Opt-in extras: hand tracking (HandLandmarker), voice-activity + audio-mouth-sync (Web Audio API). Session recording + JSON replay shipped 2026-05-17. See `web/amispoof/README.md` for the deployment runbook and `ROADMAP.md` "Browser Port v0.1.0" for the full module inventory.
Comment thread web/amispoof/index.html
Comment on lines 9 to 12
<meta
name="description"
content="Am I spoof? amispoof answers the question in the browser. Open face anti-spoof + liveness tester — 19 analyzers (MiniFASNet, blink, rPPG, gaze, blendshapes, 3D pose, audio-mouth sync, ...) + 15-axis passive liveness-proof scorer running entirely client-side. No server, no upload. Point your camera at a printed photo or another screen and watch the LIVE / SPOOF verdict flip in seconds."
content="Am I spoof? amispoof answers the question in the browser. Open face anti-spoof + liveness tester — 23 analyzers (20 active by default; hand & voice/audio opt-in — MiniFASNet, blink, rPPG, gaze, blendshapes, 3D pose, audio-mouth sync, ...) + 18-axis passive liveness-proof scorer running entirely client-side. No server, no upload. Point your camera at a printed photo or another screen and watch the LIVE / SPOOF verdict flip in seconds."
/>
Comment thread web/amispoof/index.html
Comment on lines 28 to 31
<meta
property="og:description"
content="Am I spoof? amispoof answers it in the browser. 19 analyzers, 3 gates, and a 15-axis passive liveness-proof scorer via onnxruntime-web + MediaPipe. Test printed-photo, phone-screen replay, deepfake, occlusion and dark-room attacks against a live LIVE/SPOOF verdict in seconds. No server, no upload."
content="Am I spoof? amispoof answers it in the browser. 23 analyzers (20 active by default; hand & voice/audio opt-in), 3 gates, and an 18-axis passive liveness-proof scorer via onnxruntime-web + MediaPipe. Test printed-photo, phone-screen replay, deepfake, occlusion and dark-room attacks against a live LIVE/SPOOF verdict in seconds. No server, no upload."
/>
Comment thread web/amispoof/index.html
Comment on lines 91 to 95
"name": "Am I spoof?",
"acceptedAnswer": {
"@type": "Answer",
"text": "amispoof answers the question in your browser in a few seconds — open https://amispoof.fivucsas.com/, grant camera access, and the page runs 19 anti-spoof analyzers + a 15-axis passive liveness-proof scorer on your face. The verdict (LIVE or SPOOF) appears in real time with per-axis evidence. Nothing is uploaded — all inference happens client-side in WebAssembly."
"text": "amispoof answers the question in your browser in a few seconds — open https://amispoof.fivucsas.com/, grant camera access, and the page runs 23 anti-spoof analyzers (20 active by default) + an 18-axis passive liveness-proof scorer on your face. The verdict (LIVE or SPOOF) appears in real time with per-axis evidence. Nothing is uploaded — all inference happens client-side in WebAssembly."
}
Comment thread README.md
- [ ] iBeta PAD-Level-1 browser-bundle submission package.

Live tester: https://amispoof.fivucsas.com/ (the old https://fivucsas.com/amispoof/ now 301s) — **19 analyzers + 3 gates + 15-axis passive liveness-proof scorer** running entirely client-side. Default-on: 17 analyzers covering the original ten plus the seven blendshape/3D-pose unlocks (eyebrow motion, blink symmetry, gaze, expression dynamics, 3D pose consistency, behavioural pattern, plus temporal + background grid brought across from `src/`). Opt-in extras: background motion (MediaPipe SelfieSegmenter), hand tracking (HandLandmarker), voice-activity + audio-mouth-sync (Web Audio API). Session recording + JSON replay shipped 2026-05-17. See `web/amispoof/README.md` for the deployment runbook and `ROADMAP.md` "Browser Port v0.1.0" for the full module inventory.
Live tester: https://amispoof.fivucsas.com/ (the old https://fivucsas.com/amispoof/ now 301s) — **23 analyzers + 3 gates + 18-axis passive liveness-proof scorer** running entirely client-side. Default-on: 20 analyzers covering the original ten plus the blendshape/3D-pose unlocks (eyebrow motion, blink symmetry, gaze, expression dynamics, 3D pose consistency, behavioural pattern), temporal + background grid brought across from `src/`, and background motion (MediaPipe SelfieSegmenter). Opt-in extras: hand tracking (HandLandmarker), voice-activity + audio-mouth-sync (Web Audio API). Session recording + JSON replay shipped 2026-05-17. See `web/amispoof/README.md` for the deployment runbook and `ROADMAP.md` "Browser Port v0.1.0" for the full module inventory.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants