Update app.py

app.py

@@ -64,24 +64,35 @@ def predict(req: PredictRequest):
         else:
             raise HTTPException(status_code=400, detail="Must provide 'image' (base64) or 'image_url'.")
 
+        # 4. Execute AI Math
         # 4. Execute AI Math
         results = pipe(img)
         
-        # 5. Format to exact Task 25 specifications
-        scores_dict = {}
-        for res in results:
-            raw_label = res['label'].upper()
-            # Map standard model output to strict spec requirements
-            final_label = "DEEPFAKE" if "FAKE" in raw_label else "REAL"
-            scores_dict[final_label] = round(res['score'], 4)
-            
-        top_pred = max(scores_dict, key=scores_dict.get)
+        # 5. Sensitivity Logic (The Hackathon Fix)
+        # We manually check the fake score. If it's > 0.01, we flag it.
+        fake_score = 0.0
+        real_score = 0.0
         
+        for res in results:
+            if "FAKE" in res['label'].upper():
+                fake_score += res['score']
+            else:
+                real_score += res['score']
+
+        # THE FIX: Even if the AI says 90% Real, if it's 10% Fake, we flag it.
+        # This is a common strategy for detecting high-quality modern deepfakes.
+        if fake_score > 0.10:  # Adjust this (0.01 to 0.10) to find the sweet spot
+            top_pred = "DEEPFAKE"
+        else:
+            top_pred = "REAL"
+
         return {
             "prediction": top_pred,
-            "confidence": scores_dict[top_pred],
-            "scores": scores_dict
+            "confidence": round(max(fake_score, real_score), 4),
+            "scores": {
+                "REAL": round(real_score, 4),
+                "DEEPFAKE": round(fake_score, 4)
+            }
         }
-        
     except Exception as e:
         raise HTTPException(status_code=400, detail=f"Failed to process face: {str(e)}")