gradio_app.py

hackaprompt/gradio_app.py

@@ -118,10 +118,16 @@ with gr.Blocks() as demo:
     evaluator_0 = gr.State(get_evaluator(level=0, completer=None))
 
     gr.Markdown(
-        """
-    # TRAIL Hands-on Exercise: Exploring Jailbreaking & Gen AI Risks  
-    
-    In the presentation, we explored key risks associated with generative AI, including **jailbreaking, prompt engineering exploits, and data leakage**. Now, this hands-on exercise will give you practical experience in understanding how these vulnerabilities work in real-time.  
+    """
+    <div style="display: flex; align-items: center;">
+         <img src="https://mila.quebec/sites/default/files/media-library/image/4032/milalogowebcoulrgb.png" width="120" style="margin-right: 0px;">
+         <h1 style="margin: 0;">Hands-on Exercise: Exploring Jailbreaking & Gen AI Risks</h1>
+    </div>
+
+    This exercise is part of the TRAIL Responsible Gen AI Risk Module, designed to provide hands-on experience with the challenges of Gen AI. 
+
+    In the presentation, we explored key risks associated with generative AI, including **jailbreaking, prompt engineering exploits, and data leakage**. Now, this hands-on exercise will give you practical experience in understanding how these vulnerabilities work in real-time. 
+    While real-world risks can be severe, this exercise presents a controlled, simplified version.
     
     ### Your Task  
     Your goal is to manipulate a language model using carefully crafted prompts to bypass safeguards and generate a specific response. This exercise will help you: