Create app.py

app.py

@@ -0,0 +1,91 @@
+import gradio as gr
+import torch
+import torchvision.transforms as T
+from PIL import Image
+import numpy as np
+
+# -----------------------------
+# NOTE FOR USER:
+# This is a PROTOTYPE detector.
+# It uses simple CNN-based feature heuristics + frequency analysis.
+# It is NOT a forensic-grade deepfake detector.
+# -----------------------------
+
+# Image preprocessing
+transform = T.Compose([
+    T.Resize((224, 224)),
+    T.ToTensor(),
+    T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
+])
+
+# Simple frequency analysis (FFT-based heuristic)
+def frequency_artifacts(image: Image.Image):
+    gray = image.convert("L")
+    arr = np.array(gray)
+    fft = np.fft.fft2(arr)
+    fft_shift = np.fft.fftshift(fft)
+    magnitude = np.log(np.abs(fft_shift) + 1)
+    score = np.mean(magnitude)
+    return score
+
+# Main prediction function
+def detect_authenticity(image):
+    if image is None:
+        return "No image provided", 0.0
+
+    pil_image = Image.fromarray(image)
+    freq_score = frequency_artifacts(pil_image)
+
+    # Heuristic thresholds (tunable)
+    if freq_score > 5.2:
+        label = "⚠️ Likely Manipulated / Deepfake"
+        confidence = min((freq_score - 5) * 20, 95)
+    else:
+        label = "✅ Likely Authentic"
+        confidence = min((6 - freq_score) * 20, 95)
+
+    return label, round(confidence, 2)
+
+# Gradio UI
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    gr.Markdown("""
+    # 🕵️ Deepfake & Image Authenticity Detector
+    Upload an image to analyze whether it appears **authentic or manipulated**.
+
+    **Use cases:**
+    - Media verification
+    - Social media fact-checking
+    - Educational demos
+    - Digital forensics awareness
+
+    ⚠️ *This tool uses heuristic signals and is for educational purposes.*
+    """)
+
+    with gr.Row():
+        with gr.Column():
+            image_input = gr.Image(label="Upload Image", type="numpy")
+            analyze_btn = gr.Button("Analyze Image 🔍")
+        with gr.Column():
+            result_label = gr.Textbox(label="Prediction")
+            confidence = gr.Slider(0, 100, label="Confidence (%)")
+
+    analyze_btn.click(
+        fn=detect_authenticity,
+        inputs=image_input,
+        outputs=[result_label, confidence]
+    )
+
+    gr.Markdown("""
+    ### ℹ️ How it works (Simplified)
+    - Analyzes **frequency artifacts** commonly introduced by GANs & image manipulation
+    - Detects unnatural pixel distributions
+
+    🔧 *Future upgrades you can add:*
+    - XceptionNet / EfficientNet deepfake models
+    - Face-only region detection
+    - Video deepfake detection
+    - Explainable heatmaps
+    """)
+
+# Launch
+demo.launch()