Update app.py

app.py

@@ -2,14 +2,23 @@ import streamlit as st
 import torch
 from transformers import BertTokenizer, BertForSequenceClassification
 
+# ✅ Ensure set_page_config is the first Streamlit command
+st.set_page_config(page_title="Scam Slayer", layout="centered")
+
 # Load model from Hugging Face
 MODEL_NAME = "sellestas/scam_slayer_model"
-tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")
-model = BertForSequenceClassification.from_pretrained(MODEL_NAME)
-device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-model.to(device)
-model.eval()
 
+try:
+    tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")
+    model = BertForSequenceClassification.from_pretrained(MODEL_NAME)
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+    model.to(device)
+    model.eval()
+    st.success("✅ Scam Slayer Model Loaded Successfully!")
+except Exception as e:
+    st.error(f"❌ Error loading model: {e}")
+
+# Function to classify email
 def classify_email(text):
     inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True, max_length=128)
     inputs = {k: v.to(device) for k, v in inputs.items()}
@@ -17,22 +26,41 @@ def classify_email(text):
         outputs = model(**inputs)
         probabilities = torch.nn.functional.softmax(outputs.logits, dim=-1)
         confidence, prediction = torch.max(probabilities, dim=-1)
-    
-    label_map = {0: "Non-Malicious", 1: "Malicious"}
+
+    label_map = {0: "Non-Malicious ✅", 1: "Malicious 🚨"}
     return label_map[prediction.item()], confidence.item() * 100
 
-# Streamlit UI
-st.set_page_config(page_title="Scam Slayer", layout="centered")
+# UI Layout
 st.image("logo.png", width=150)
 st.title("🛡️ Scam Slayer - AI Email Threat Detector")
 st.markdown("### 🔍 Detect phishing and malicious emails instantly!")
 
+# Sidebar About Button
+with st.sidebar:
+    if st.button("ℹ️ About Scam Slayer"):
+        st.markdown("""
+        ## 📌 About Scam Slayer  
+        **AI-powered cybersecurity tool** to detect phishing threats.  
+
+        ✅ **Purpose**: Identify and stop phishing attacks.  
+        ✅ **Model**: Fine-tuned BERT-based classifier.  
+        ✅ **Developed for**: **SANS AI Cybersecurity Hackathon 2025**.  
+        ✅ **Features**:  
+        - Detects **Malicious & Non-Malicious** emails  
+        - Uses **NLP** for content analysis  
+        - Provides a **confidence score** (1-100%)  
+
+        **Version**: 1.0.0  
+        """)
+
+# Email Input
 email_text = st.text_area("✉️ Paste the email content below:", height=200)
 
-if st.button("Detect Scam", help="Click to analyze the email content"):
+# Detect Scam Button
+if st.button("🚀 Detect Scam", help="Click to analyze the email content"):
     if email_text.strip():
         category, confidence = classify_email(email_text)
         st.success(f"**🔹 Result: {category} ({confidence:.2f}% Confidence)**")
-        st.markdown("\n ✅ Stay vigilant! 🚀")
+        st.markdown("✅ **Stay vigilant against scams!** 🚀")
     else:
         st.warning("⚠️ Please enter email content to analyze!")