source code added

`src` folder contains model.py and serve.py files

src/__init__.py

@@ -0,0 +1 @@
+

src/model.py

@@ -0,0 +1,87 @@
+import torch
+from torch import nn
+import torch.nn.functional as F
+
+
+malware_classes = ['7ev3n', 'APosT', 'Adposhel', 'Agent', 'Agentb', 'Allaple', 'Alueron.gen!J', 'Amonetize', 
+                   'Androm', 'Bashlite', 'Bingoml', 'Blacksoul', 'BrowseFox', 'C2LOP.gen!g', 'Convagent', 'Copak', 
+                   'Delf', 'Dialplatform.B', 'Dinwod', 'Elex', 'Emotet', 'Escelar', 'Expiro', 'Fakerean', 'Fareit', 
+                   'Fasong', 'GandCrab', 'GlobelImposter', 'GootLoader', 'HLLP', 'HackKMS', 'Hlux', 'IcedId', 'Infy', 
+                   'Inject', 'Injector', 'InstallCore', 'KRBanker', 'Koadic', 'Kryptik', 'Kwampirs', 'Lamer', 
+                   'LemonDuck', 'Loki', 'Lolyda.AA1', 'Lolyda.AA2', 'Mimail', 'MultiPlug', 'Mydoom', 'Neoreklami', 
+                   'Neshta', 'NetWireRAT', 'Ngrbot', 'OnlinerSpambot', 'Orcus', 'Padodor', 'Plite', 'PolyRansom', 
+                   'QakBot', 'QtBot', 'Qukart', 'REvil', 'Ramdo', 'Regrun', 'Rekt Loader', 'Sakula', 'Salgorea', 
+                   'Scar', 'SelfDel', 'Small', 'Snarasite', 'Stantinko', 'Trickpak', 'Upantix', 'Upatre', 'VB', 
+                   'VBA', 'VBKrypt', 'VBNA', 'Vilsel', 'Vobfus', 'WBNA', 'Wecod', 'XTunnel', 'Zenpak', 'Zeus', 'benign']
+
+class DenseLayer(nn.Module):
+    def __init__(self, in_channels, growth_rate, bn_size):
+        super(DenseLayer, self).__init__()
+        self.bn1 = nn.BatchNorm2d(in_channels)
+        self.conv1 = nn.Conv2d(in_channels, bn_size * growth_rate, kernel_size=1, bias=False)
+        self.bn2 = nn.BatchNorm2d(bn_size * growth_rate)
+        self.conv2 = nn.Conv2d(bn_size * growth_rate, growth_rate, kernel_size=3, padding=1, bias=False)
+        
+    def forward(self, x):
+        out = self.conv1(F.relu(self.bn1(x)))
+        out = self.conv2(F.relu(self.bn2(out)))
+        return torch.cat([x, out], 1)
+
+class DenseBlock(nn.Module):
+    def __init__(self, num_layers, in_channels, growth_rate, bn_size):
+        super(DenseBlock, self).__init__()
+        layers = []
+        for i in range(num_layers):
+            layers.append(DenseLayer(in_channels + i * growth_rate, growth_rate, bn_size))
+        self.layers = nn.Sequential(*layers)
+    
+    def forward(self, x):
+        return self.layers(x)
+
+class TransitionLayer(nn.Module):
+    def __init__(self, in_channels, out_channels):
+        super(TransitionLayer, self).__init__()
+        self.bn = nn.BatchNorm2d(in_channels)
+        self.conv = nn.Conv2d(in_channels, out_channels, kernel_size=1, bias=False)
+        self.pool = nn.AvgPool2d(kernel_size=2, stride=2)
+        
+    def forward(self, x):
+        out = self.conv(F.relu(self.bn(x)))
+        return self.pool(out)
+
+class MalwareNet(nn.Module):
+    def __init__(self, growth_rate=32, block_config=(6, 12, 24, 16), num_init_features=64, bn_size=4, compression_rate=0.5, num_classes=87):
+        super(MalwareNet, self).__init__()
+        
+        # First convolution
+        self.features = nn.Sequential(
+            nn.Conv2d(3, num_init_features, kernel_size=7, stride=2, padding=3, bias=False),
+            nn.BatchNorm2d(num_init_features),
+            nn.ReLU(inplace=True),
+            nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
+        )
+        
+        # Dense blocks
+        num_features = num_init_features
+        for i, num_layers in enumerate(block_config):
+            block = DenseBlock(num_layers, num_features, growth_rate, bn_size)
+            self.features.add_module(f'denseblock{i+1}', block)
+            num_features += num_layers * growth_rate
+            if i != len(block_config) - 1:
+                transition = TransitionLayer(num_features, int(num_features * compression_rate))
+                self.features.add_module(f'transition{i+1}', transition)
+                num_features = int(num_features * compression_rate)
+        
+        # Final batch norm
+        self.features.add_module('norm5', nn.BatchNorm2d(num_features))
+        
+        # Linear layer
+        self.classifier = nn.Linear(num_features, num_classes)
+        
+    def forward(self, x):
+        features = self.features(x)
+        out = F.relu(features)
+        out = F.adaptive_avg_pool2d(out, (1, 1))
+        out = torch.flatten(out, 1)
+        out = self.classifier(out)
+        return out

src/serve.py

@@ -0,0 +1,73 @@
+from PIL import Image
+from torchvision import transforms
+import torch
+import os
+from fastapi import FastAPI, HTTPException
+from fastapi.responses import JSONResponse
+from io import BytesIO
+
+# from dotenv import load_dotenv
+from .model import MalwareNet, malware_classes  # assuming malware_classes contains class names
+
+# load_dotenv()
+
+app = FastAPI()
+
+# Preprocessing function for the model
+def preprocess_image(image_path):
+    image = Image.open(image_path).convert("RGB")
+    preprocess = transforms.Compose([
+        transforms.Resize((224, 224)),  # Resize to the input size expected by the model
+        transforms.ToTensor(),          # Convert to tensor
+        transforms.Normalize(           # Normalize using model's requirements (e.g. ImageNet)
+            mean=[0.485, 0.456, 0.406], 
+            std=[0.229, 0.224, 0.225]
+        )
+    ])
+    return preprocess(image).unsqueeze(0)  # Add batch dimension
+
+# Load model and its weights
+def load_model():
+    model = MalwareNet()
+    base_dir = os.path.dirname(os.path.abspath(__file__))
+    model_location = os.path.join(base_dir, '../model/malwareNet.pt')  # Relative path to the model file
+    state_dict = torch.load(model_location, map_location=torch.device('cpu'), weights_only=True)
+    model.load_state_dict(state_dict)
+    model.eval()  # Set the model to evaluation mode
+    return model
+
+@app.get("/")
+def status():
+    return {"status": "ok"}
+
+@app.post("/predict")
+async def predict(data: dict):
+    image_path = data.get("image_url")
+    if not os.path.exists(image_path):
+        raise HTTPException(status_code=400, detail="Image path does not exist.")
+
+    try:
+        # Load and preprocess the image
+        img_tensor = preprocess_image(image_path)
+
+        # Load the model and make the prediction
+        model = load_model()
+        with torch.no_grad():  # No gradient calculation is needed
+            prediction = model(img_tensor)
+
+        # Get the predicted class
+        predicted_class = malware_classes[torch.argmax(prediction).item()]
+
+        return JSONResponse(content={"image": image_path, "prediction": predicted_class})
+
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Error processing the image: {e}")
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(
+        "src.serve:app",
+        host=os.environ.get("HOST", "localhost"),
+        port=int(os.environ.get("PORT", 5000)),
+        reload=True,
+    )