Deepfake-Detect-Siglip2

Deepfake-Detect-Siglip2 is an image classification vision-language encoder model fine-tuned from google/siglip2-base-patch16-224 for a single-label classification task. It is designed to detect whether an image is real or a deepfake using the SiglipForImageClassification architecture.

The model categorizes images into two classes:

• Class 0: "Fake" – The image is detected as a deepfake or manipulated.
• Class 1: "Real" – The image is classified as authentic and unaltered.

Run with Transformers🤗

!pip install -q transformers torch pillow gradio

import gradio as gr
from transformers import AutoImageProcessor
from transformers import SiglipForImageClassification
from transformers.image_utils import load_image
from PIL import Image
import torch

# Load model and processor
model_name = "prithivMLmods/Deepfake-Detect-Siglip2"
model = SiglipForImageClassification.from_pretrained(model_name)
processor = AutoImageProcessor.from_pretrained(model_name)

def deepfake_detection(image):
    """Classifies an image as Fake or Real."""
    image = Image.fromarray(image).convert("RGB")
    inputs = processor(images=image, return_tensors="pt")
    
    with torch.no_grad():
        outputs = model(**inputs)
        logits = outputs.logits
        probs = torch.nn.functional.softmax(logits, dim=1).squeeze().tolist()
    
    labels = model.config.id2label
    predictions = {labels[i]: round(probs[i], 3) for i in range(len(probs))}
    
    return predictions

# Create Gradio interface
iface = gr.Interface(
    fn=deepfake_detection,
    inputs=gr.Image(type="numpy"),
    outputs=gr.Label(label="Detection Result"),
    title="Deepfake Detection Model",
    description="Upload an image to determine if it is Fake or Real."
)

# Launch the app
if __name__ == "__main__":
    iface.launch()

Intended Use:

The Deepfake-Detect-Siglip2 model is designed to distinguish between real and fake (deepfake) images. It is useful for identifying AI-generated or manipulated content.

Potential Use Cases:

• Deepfake Detection: Identifying AI-generated fake images.
• Content Verification: Assisting social media platforms in filtering manipulated content.
• Forensic Analysis: Supporting cybersecurity and investigative research on fake media.
• Media Authenticity Checks: Helping journalists and fact-checkers verify image credibility.