update introduction markdown

app.py

@@ -72,9 +72,13 @@ def main():
         
         gr.Markdown('''## Generate Adversarial Image with Fast Gradient Sign Method
                     
-                    Given an input image and a neural network, the adversarial image can be generated from 
+                    Fast Gradient Sign Method was introduced in the paper [Explaining and Harnessing Adversarial Examples](https://arxiv.org/abs/1412.6572).
+
+                    Given an input image and a neural network, an adversarial image can be generated by applying a small perturbation in the direction of the gradient that maximizes the loss to the input image.
                     
-                    <code>adv_img = input_img + epsilon * sign(input_img.grad)</code>
+                    <code>adv_img = input_img + epsilon * sign(input_img.grad)</code>.
+
+                    The parameter `epsilon` controls the maximum bound of the perturbation.
                     
                     ''')