Anti-Detect Automation Detection v3

.gitmodules

@@ -1,6 +1,6 @@
-[submodule "src/challenges/ab_sniffer"]
-	path = src/challenges/ab_sniffer
-	url = https://github.com/RedTeamSubnet/ab-sniffer-challenge.git
 [submodule "src/challenges/bot_virus"]
 	path = src/challenges/bot_virus
 	url = https://github.com/RedTeamSubnet/bot-virus-challenge.git
+[submodule "src/challenges/ada_detection"]
+	path = src/challenges/ada_detection
+	url = https://github.com/RedTeamSubnet/ada-detection-challenge.git

docs/challenges/.nav.yml

@@ -3,10 +3,10 @@ nav:
   - Active Challenges:
       - ab_sniffer: ./ab_sniffer
       - bot_virus: ./bot_virus
+      - ada_detection: ./ada_detection
   - Inactive Challenges:
       - flowradar: ./flowradar
       - flowprint: ./flowprint
       - historical_fingerprinter: ./historical_fingerprinter
       - dev_fingerprinter: ./dev_fingerprinter
-      - ada_detection: ./ada_detection
       - humanize_behaviour: ./humanize_behaviour

docs/challenges/README.md

@@ -69,5 +69,5 @@ Follow these steps to successfully submit your challenge solution:
 - **[FlowRadar v2](flowradar/README.md)** Train and run a two-stage model pipeline for VPN detection from network flow data.
 - **[FlowPrint v1](flowprint/README.md) — Inactive** Former OS-classification challenge; submissions are rejected.
 - **[Humanize Behaviour](humanize_behaviour/README.md)** Develop bot scripts that mimic natural human interaction with web forms.
-- **[Anti-Detect Automation Detection (AAD)](ada_detection/README.md)** Detect browser automation inside anti-detect environments where fingerprints are masked.
+- **[Anti-Detect Browser Detection (ADA)](ada_detection/README.md)** Identify which commercial anti-detect browser is driving a session, without firing on human traffic.
 - **[Device Fingerprinter](dev_fingerprinter/README.md) Inactive** Create browser SDKs that accurately fingerprint and identify devices.

docs/challenges/ada_detection/README.md

@@ -1,89 +1,69 @@
-# Anti-Detect Automation Detection (AAD) Challenge
+# Anti-Detect Browser Detection (ADA) Challenge
 
 ## Overview
 
-The **Anti-Detect Automation Detection (AAD)** challenge evaluates a participant's ability to reliably detect browser automation frameworks operating inside anti-detect browsers, while preserving human safety.
+The **Anti-Detect Browser Detection (ADA)** challenge tests miners' ability to identify which
+**commercial anti-detect browser** is driving a session, while leaving genuine human traffic
+untouched.
 
-Evaluation runs simulate real-world anti-detect usage where static signals are masked and fingerprints are fresh. Detection must rely on runtime behavior and orchestration patterns.
+Each target is a paid desktop application that launches a managed profile and is driven over
+its own loopback API. There is no WebDriver or CDP automation flag to key on, so detection
+must rely on the product artifacts the anti-detect browser itself leaves behind in the page
+environment.
 
-## Anti-Detect Environment
+## General Technical Requirements
 
-Each evaluation run involves:
+- **Development Language**: JavaScript (ES6+), one self-contained detector per target
+- **Environment**: Docker container environment
+- **Architecture**: amd64 (ARM64 at your own risk)
+- **State**: Stateless execution with no persistence between runs
 
-- A **fresh NST-Browser profile**.
-- An **isolated Docker container per framework**.
-- Masks for browser fingerprints and no shared state between runs.
+## General Guidelines
 
-!!! Info "NST-Browser Dependency"
-    Participants need an API key from the [NSTBrowser](https://www.nstbrowser.io/en/pricing) dashboard (Professional plan recommended) for local testing.
+- **Detection Method**: Analyze product-specific artifacts, patched APIs, injected objects,
+  and behavioral patterns.
+- **Execution Modes**: Detectors are tested in both headed and headless modes.
+- **Human Safety**: A normal headed browser must not trigger a browser or headless detector.
+  Any false positive on a human task drives the score to zero.
+- **Prohibited Method**: Browser fingerprinting is not allowed.
 
-## Features of ADA Detection v2
+## Plagiarism Check
 
-- **Hardened NSTBrowser Environment**: Advanced obfuscation including dynamic fingerprinting and hardware simulation (8GB RAM, 16 Cores).
-- **Engine-Level Stealth**: `AutomationControlled` flags are disabled at the browser engine level to eliminate static detection signals.
-- **Fail-Fast Scoring**: High-stakes evaluation where missing critical targets (Selenium) or exceeding miss limits results in an immediate 0.0 score.
-- **Protocol-Level Verification**: Mandatory detection of low-level communication patterns (Webdriver and WebSocket).
-- **Selenium Safety Gate**: Mandatory detection of `seleniumbase` and `selenium_driverless` is required for incentive eligibility.
-- **Similarity/time decay**: Similarity penalties apply to lookalike submissions; scores decay over 15 days to encourage refreshed heuristics.
-
-## Evaluation Flow
+We maintain strict originality standards:
 
-1. **Submission Received**: Detection scripts are submitted via the `/score` endpoint.
-2. **Task Generation**: A randomized sequence of multiple automation framework runs and human interactions is generated.
-3. **NST-Browser Launch**: A clean instance is started for each task.
-4. **Execution**: Automation frameworks connect via WebSocket or WebDriver, while humans interact manually.
-5. **Detection Phase**: Scripts may emit detection payloads to `/_payload`.
-6. **Scoring**: Results are aggregated and normalized using the Fail-Fast pillars.
+- All submissions are compared against other miners' detectors.
+- 100% similarity = zero score.
+- Similarity above 60% will result in rejection of the submission.
 
-## Technical Constraints
+## Submission Path
 
-- **Language**: JavaScript (ES6+)
-- **Environment**: NST-Browser only
-- **Architecture**: Docker (amd64 recommended)
-- **State**: Stateless execution with no persistence between runs.
+**Dedicated Path:** [`examples/miner_commit/src/commit/`](https://github.com/RedTeamSubnet/ada-detection-challenge/tree/main/examples/miner_commit/src/commit/)
 
-## Plagiarism Policy
+Place your detection module files in this directory before building your commit:
 
-We maintain strict originality standards:
+- `ads_power.js`
+- `dolphin_anty.js`
+- `gologin.js`
+- `headless.js`
+- `multilogin.js`
+- `octo.js`
 
-- All submissions are compared against other participants' SDKs.
-- 100% similarity = zero score.
-- Similarity above 60% results in proportional score penalties based on the **detected similarity percentage**.
+## Challenge Versions
 
-## Submission Path
+**Current:**
 
-**Dedicated Path:** [templates/commit/src/detections/](https://github.com/RedTeamSubnet/ada-detection-challenge/tree/main/templates/commit/src/detections/)
-
-Submit your detection scripts as a JSON payload with the following structure:
-
-```json
-{
-  "detection_files": [
-    { "file_name": "nodriver.js", "content": "..." },
-    { "file_name": "playwright.js", "content": "..." },
-    { "file_name": "patchright.js", "content": "..." },
-    { "file_name": "puppeteer.js", "content": "..." },
-    { "file_name": "puppeteer_extra.js", "content": "..." },
-    { "file_name": "zendriver.js", "content": "..." },
-    { "file_name": "selenium_driverless.js", "content": "..." },
-    { "file_name": "seleniumbase.js", "content": "..." },
-    { "file_name": "webdriver.js", "content": "..." },
-    { "file_name": "websocket.js", "content": "..." }
-  ]
-}
-```
-
-Each file must be named exactly as shown and contain self-contained JavaScript (ES6+) detection logic.
+- [**v3**](./v3.md) - Commercial anti-detect browser identification, independent headless
+  classification, and human verification
 
-## Challenge Versions
+**Deprecated:**
 
-- [**v2** (Active after Feb 14, 2026 14:00 UTC)](depricated/v2.md) - Hardened detection with Fail-Fast scoring
-- [**v1** (Deprecated)](./depricated/v1.md)
+- [v2](./depricated/v2.md) - NSTBrowser-hardened automation detection with fail-fast scoring
+- [v1](./depricated/v1.md)
 
 ## Resources & Guides
 
 - [Building a Submission Commit](../../miner/workflow/3.build-and-publish.md) - General submission instructions
-- [NSTBrowser Official](https://www.nstbrowser.io/en/pricing) - Professional plan required for local testing
+- [ADA-3 Testing Manual](./testing_manuals.md) - Local validation and environment guidance
 - [Challenge Repository](https://github.com/RedTeamSubnet/ada-detection-challenge/)
 - [Miner Repository](https://github.com/RedTeamSubnet/miner/)
 

docs/challenges/ada_detection/depricated/v1.md

@@ -8,7 +8,7 @@ title: Anti-Detect Automation Detection
 
 **ADA Detection v1** focuses on behavioral detection inside NST-Browser where traditional static signals are masked. This version uses a payload-based flow with strict human safety requirements.
 
-For general challenge information, environment details, and plagiarism policies, please refer to the [AAD README](../README.md).
+For general challenge information, environment details, and plagiarism policies, please refer to the [ADA README](../README.md).
 
 ---
 
@@ -58,7 +58,7 @@ Submissions must follow this structure:
 
 ## Scoring System
 
-AAD scoring is continuous, normalized, and strict, combining three main components before being normalized into a final score.
+ADA scoring is continuous, normalized, and strict, combining three main components before being normalized into a final score.
 
 * **Human Accuracy:** This is the most critical component. Your submission must not flag real human users as bots or automation. You are allowed a maximum of 2 mistakes; exceeding this limit results in an immediate **final score of 0.0** (human safety kill switch). For scoring, you start with 1.0 point, and each mistake reduces this component by 0.1.
 

docs/challenges/ada_detection/depricated/v2.md

@@ -16,7 +16,7 @@ title: Anti-Detect Automation Detection v2
 
 Scoring has transitioned to a **Fail-Fast** model, emphasizing accuracy across three critical pillars: Human Detection, Framework Detection (with a Selenium Safety Gate), and Protocol Accuracy.
 
-For general challenge information, environment details, and plagiarism policies, please refer to the [AAD README](../README.md).
+For general challenge information, environment details, and plagiarism policies, please refer to the [ADA README](../README.md).
 
 ---