From d90baac3f619f5a12f932b6204c193c8f10de344 Mon Sep 17 00:00:00 2001
From: ramtherunner <34756719+ramtherunner@users.noreply.github.com>
Date: Fri, 16 Oct 2020 00:26:43 -0700
Subject: [PATCH] Update adversarial-ml-101.md

---
 pages/adversarial-ml-101.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/pages/adversarial-ml-101.md b/pages/adversarial-ml-101.md
index 78f7e6e..d69ed0c 100644
--- a/pages/adversarial-ml-101.md
+++ b/pages/adversarial-ml-101.md
@@ -5,7 +5,7 @@ Informally, Adversarial ML is "subverting machine learning systems for fun and p
 
 Consider a typical ML pipeline shown below that is gated behind an API, wherein the only way to use the model is to send a query and observe an response. In this example, we assume a blackbox setting: the attacker does **NOT** have direct access to the training data, no knowledge of the algorithm used and no source code of the model. The attacker only queries the model and observes the response.
 
-![alt text](images/AdvML101)
+![Adversarial ML 101](/images/AdvML101.PNG)
 
 Here are some of the adversarial ML attacks that an adversary can perform on this system:
 | Attack 		 				| Overview	|