test

Dockerfile.txt

@@ -0,0 +1,7 @@
+FROM ubuntu
+WORKDIR /app
+COPY . /app
+RUN apt update && apt install -y python3 python3-pip ffmpeg nano 
+RUN pip install flask transformers librosa torch torchaudio gunicorn
+EXPOSE 8080
+CMD ["gunicorn", "-b", ":8080", "-w", "2", "host:app"]

flag1.txt

@@ -0,0 +1 @@
+kernel{e97549a285227268bd826dd61d097016}

flag2.txt

@@ -0,0 +1 @@
+kernel{91edded0465d0ba9ee78981c63b864f8}

host.py

@@ -0,0 +1,143 @@
+from flask import Flask, render_template, request, jsonify
+from transformers import Wav2Vec2FeatureExtractor, UniSpeechSatForXVector
+import torchaudio
+import torch
+import io
+import librosa
+from scipy.spatial.distance import cosine
+import numpy as np
+import os
+# brew install ffmpeg
+# pip install flask transformers librosa torch torchaudio
+
+app = Flask(__name__, static_url_path='/static')
+
+# https://www.youtube.com/watch?v=NjR6TyHgAho first 30s
+mp3_file_path = "arnold.mp3"
+
+# https://neets.ai/ "With great power comes great responsibility"
+mp3_file_path2 = 'arnold2.wav'
+
+flag1=""
+flag2=""
+
+with open("flag1.txt") as f:
+ flag1=f.read()
+with open("flag2.txt") as f:
+ flag2=f.read()
+
+# Load feature extractor and model
+themodel = "microsoft/unispeech-sat-large-sv"
+if os.path.exists("model"):
+    themodel = "model"
+feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained(themodel)
+model = UniSpeechSatForXVector.from_pretrained(themodel)
+
+# Preprocess audio function to convert audio to mono 16khz
+def preprocess_audio(audio_data):
+    waveform, sample_rate = torchaudio.load(audio_data)
+    if waveform.shape[0] > 1:
+        waveform = torch.mean(waveform, dim=0, keepdim=True)
+    if sample_rate != 16000:
+        waveform = torchaudio.transforms.Resample(sample_rate, 16000)(waveform)
+    waveform = waveform.squeeze().numpy()
+    return waveform
+
+@app.route('/')
+def index():
+    return render_template('index.html')
+
+@app.route('/chal2')
+def chal2():
+    return render_template('chal2.html')
+
+# Hugging faces doesn't run an api for us anymore so processing data against a model needs to be done locally now
+# https://www.ktskumar.com/2021/12/introduction-to-voice-authentication-using-javascript/
+# https://hf.space/gradioiframe/microsoft/unispeech-speaker-verification/api/predict
+# You can buy something similiar through Azure, perhaps microsoft just wanted to commercialize this
+@app.route('/compare_audio', methods=['POST'])
+def compare_audio():
+    try:
+        # Get the recorded audio file from the frontend
+        recorded_audio = request.files['audio_data']
+
+        # Preprocess recorded audio
+        audio_data = preprocess_audio(recorded_audio)
+        inputs = feature_extractor(audio_data, return_tensors="pt")
+        embeddings = model(**inputs).embeddings
+        embeddings_normalized = torch.nn.functional.normalize(embeddings, dim=-1).cpu()
+
+        # Load and preprocess MP3 file for comparison
+        mp3_audio = preprocess_audio(mp3_file_path)
+        mp3_inputs = feature_extractor(mp3_audio, return_tensors="pt")
+        mp3_embeddings = model(**mp3_inputs).embeddings
+        mp3_embeddings_normalized = torch.nn.functional.normalize(mp3_embeddings, dim=-1).cpu()
+
+        # Calculate cosine similarity
+        cosine_sim = torch.nn.CosineSimilarity(dim=-1)
+        similarity = cosine_sim(embeddings_normalized, mp3_embeddings_normalized).item()
+
+        similarity = round(similarity, 3)
+
+        threshold = 0.89  # Adjust the threshold as needed
+        if similarity < threshold:
+            result = "Authorization Failed! " + str(similarity) + " < 0.890<br>Do your best Terminator impression"
+        else:
+            result = "Good job! Match: " + str(similarity) + "<br>" + flag1 + "<br><a href='/chal2'>Click here to open the next challenge</a>"
+
+        return jsonify({'result': result})
+    except Exception as e:
+        print("Caught: "+str(e))
+        return jsonify({'error': 'An error occurred during audio comparison. Im fragile please dont abuse.' })
+
+def extract_mfcc(audio_bytes):
+    # Preprocess audio
+    waveform = preprocess_audio2(audio_bytes)
+    
+    # Extract MFCC coefficients
+    mfcc = librosa.feature.mfcc(y=waveform, sr=16000, n_mfcc=13)
+
+    return mfcc
+
+def preprocess_audio2(audio_bytes):
+    # Load the audio bytes into torchaudio waveform
+    waveform, sample_rate = torchaudio.load(io.BytesIO(audio_bytes))
+    
+    # Ensure the audio has a single channel (mono)
+    if waveform.shape[0] > 1:
+        waveform = torch.mean(waveform, dim=0, keepdim=True)
+
+    # Resample the audio to 16kHz if needed
+    if sample_rate != 16000:
+        waveform = torchaudio.transforms.Resample(sample_rate, 16000)(waveform)
+
+    # Trim silence at beginning and end
+    waveform, _ = librosa.effects.trim(waveform, top_db=20)
+   
+    waveform = waveform.squeeze().numpy()
+
+    return waveform
+
+@app.route('/compare_audio2', methods=['POST'])
+def compare_audio2():
+    try:
+        recorded_audio = request.files['audio_data'].read()
+        mp3_audio = open(mp3_file_path2, 'rb').read()
+
+        # Compare similarity between audio
+        mfcc1 = extract_mfcc(recorded_audio)
+        mfcc2 = extract_mfcc(mp3_audio)
+        similarity = 1 - cosine(np.mean(mfcc1, axis=1), np.mean(mfcc2, axis=1))
+        similarity = round(similarity, 3)
+        if similarity < 0.940:
+            result = "Authorization Failed! " + str(similarity) + " < 0.940<br>Say: 'With great power comes great responsibility' as Arnold Schwarzenegger"
+        else:
+            result = "Good job! Match: " + str(similarity) + "<br>" + flag2
+
+        return jsonify({'result': result})
+    except Exception as e:
+        print("Caught: "+str(e))
+        return jsonify({'error': 'An error occurred during audio comparison. Im fragile please dont abuse.'})
+
+if __name__ == '__main__':
+    app.run(host="0.0.0.0", port=8080, debug=True)

templates/chal2.html

@@ -0,0 +1,129 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+<meta charset="UTF-8">
+<meta name="viewport" content="width=device-width, initial-scale=1.0">
+<title>SKYNET Voice Authentication</title>
+<style>
+  body, html {
+    height: 100%;
+    margin: 0;
+    font-family: Arial, sans-serif;
+    color: white;
+    text-align: center;
+  }
+  .bg {
+    background-image: url('/static/skynet.png');
+    height: 100%;
+    background-position: center;
+    background-repeat: no-repeat;
+    background-size: cover;
+    position: relative;
+  }
+  .content {
+    position: absolute;
+    bottom: 10%;
+    width: 100%;
+  }
+  .controls {
+    display: flex;
+    justify-content: center;
+    align-items: center;
+  }
+  .button {
+    background-color: red;
+    color: white;
+    padding: 10px 20px;
+    border: none;
+    border-radius: 5px;
+    font-size: 16px;
+    cursor: pointer;
+    margin: 5px;
+  }
+  .button:hover {
+    background-color: darkred;
+  }
+  audio {
+    margin: 0 20px;
+  }
+</style>
+</head>
+<body>
+
+<div class="bg">
+  <div class="content">
+    <h1>Voice Authentication</h1>
+    <div class="controls">
+      <button id="recordButton" class="button">Record</button>
+      <button id="stopButton" class="button" disabled>Stop</button>
+      <audio id="audioPlayback" controls style="display:none;"></audio>
+      <button id="submitButton" class="button" style="float:right; display:none;">Submit</button>
+     </div>
+  <p id="result"></p>
+  </div>
+</div>
+
+<script>
+  let recordButton = document.getElementById('recordButton');
+  let stopButton = document.getElementById('stopButton');
+  let audioPlayback = document.getElementById('audioPlayback');
+  let submitButton = document.getElementById('submitButton');
+
+  let mediaRecorder;
+  let audioBlob;
+  let audioChunks = [];
+
+  recordButton.onclick = function() {
+    navigator.mediaDevices.getUserMedia({ audio: true })
+      .then(stream => {
+        mediaRecorder = new MediaRecorder(stream);
+        mediaRecorder.start();
+        audioChunks = [];
+
+        document.getElementById("result").innerHTML = "recording started";
+        stopButton.disabled = false;
+        recordButton.disabled = true;
+
+        mediaRecorder.ondataavailable = function(event) {
+          audioChunks.push(event.data);
+        };
+
+        mediaRecorder.onstop = function() {
+          document.getElementById("result").innerHTML = "recording stopped";
+          audioBlob = new Blob(audioChunks);
+          let audioUrl = URL.createObjectURL(audioBlob);
+          audioPlayback.src = audioUrl;
+          audioPlayback.style.display = 'block';
+        };
+      });
+  };
+
+  stopButton.onclick = function() {
+    mediaRecorder.stop();
+    stopButton.disabled = true;
+    recordButton.disabled = false;
+    submitButton.style.display = 'block';
+  };
+
+  // Submit button handler
+  submitButton.onclick = async function() {
+    document.getElementById("result").innerHTML = "Processing..."
+    //await new Promise(r => setTimeout(r, 2000));
+    console.log('Submit the audio for processing');
+    let formData = new FormData();
+    formData.append('audio_data', audioBlob);
+    fetch('/compare_audio2', {
+            method: 'POST',
+            body: formData
+     })
+    .then(response => response.json())
+    .then(data => {
+        document.getElementById("result").innerHTML = data.result;
+    })
+    .catch(error => console.error('Error:', error));
+  };
+</script>
+
+</body>
+</html>
+

templates/index.html

@@ -0,0 +1,129 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+<meta charset="UTF-8">
+<meta name="viewport" content="width=device-width, initial-scale=1.0">
+<title>SKYNET Voice Authentication</title>
+<style>
+  body, html {
+    height: 100%;
+    margin: 0;
+    font-family: Arial, sans-serif;
+    color: white;
+    text-align: center;
+  }
+  .bg {
+    background-image: url('/static/skynet.png');
+    height: 100%;
+    background-position: center;
+    background-repeat: no-repeat;
+    background-size: cover;
+    position: relative;
+  }
+  .content {
+    position: absolute;
+    bottom: 10%;
+    width: 100%;
+  }
+  .controls {
+    display: flex;
+    justify-content: center;
+    align-items: center;
+  }
+  .button {
+    background-color: red;
+    color: white;
+    padding: 10px 20px;
+    border: none;
+    border-radius: 5px;
+    font-size: 16px;
+    cursor: pointer;
+    margin: 5px;
+  }
+  .button:hover {
+    background-color: darkred;
+  }
+  audio {
+    margin: 0 20px;
+  }
+</style>
+</head>
+<body>
+
+<div class="bg">
+  <div class="content">
+    <h1>Voice Authentication</h1>
+    <div class="controls">
+      <button id="recordButton" class="button">Record</button>
+      <button id="stopButton" class="button" disabled>Stop</button>
+      <audio id="audioPlayback" controls style="display:none;"></audio>
+      <button id="submitButton" class="button" style="float:right; display:none;">Submit</button>
+     </div>
+  <p id="result"></p>
+  </div>
+</div>
+
+<script>
+  let recordButton = document.getElementById('recordButton');
+  let stopButton = document.getElementById('stopButton');
+  let audioPlayback = document.getElementById('audioPlayback');
+  let submitButton = document.getElementById('submitButton');
+
+  let mediaRecorder;
+  let audioBlob;
+  let audioChunks = [];
+
+  recordButton.onclick = function() {
+    navigator.mediaDevices.getUserMedia({ audio: true })
+      .then(stream => {
+        mediaRecorder = new MediaRecorder(stream);
+        mediaRecorder.start();
+        audioChunks = [];
+  
+        document.getElementById("result").innerHTML = "recording started";
+        stopButton.disabled = false;
+        recordButton.disabled = true;
+
+        mediaRecorder.ondataavailable = function(event) {
+          audioChunks.push(event.data);
+        };
+
+        mediaRecorder.onstop = function() {
+          document.getElementById("result").innerHTML = "recording stopped";
+          audioBlob = new Blob(audioChunks);
+          let audioUrl = URL.createObjectURL(audioBlob);
+          audioPlayback.src = audioUrl;
+          audioPlayback.style.display = 'block';
+        };
+      });
+  };
+
+  stopButton.onclick = function() {
+    mediaRecorder.stop();
+    stopButton.disabled = true;
+    recordButton.disabled = false;
+    submitButton.style.display = 'block';
+  };
+
+  // Submit button handler
+  submitButton.onclick = async function() {
+    document.getElementById("result").innerHTML = "Processing..."
+    //await new Promise(r => setTimeout(r, 2000));
+    console.log('Submit the audio for processing');
+    let formData = new FormData();
+    formData.append('audio_data', audioBlob);
+    fetch('/compare_audio', {
+            method: 'POST',
+            body: formData
+     })
+    .then(response => response.json())
+    .then(data => {
+        document.getElementById("result").innerHTML = data.result;
+    })
+    .catch(error => console.error('Error:', error));
+  };
+</script>
+
+</body>
+</html>
+