Version 1.0

7_BugHunter/README.md

@@ -7,6 +7,7 @@ You have already done the first step and created a training set of (code, vulner
 - Train a model on the data provided in 'train.txt', such as the one found in 'train.py', to find vulnerable code. (You can use any other model if you so please)
 - 'exercise.py' contains some further code you found that seems helpful.
 - Test your model on the following source code you found to see if it finds the vulnerable 'printf' statement.
+- *The emphasize of this exercise lies in pre-processing the data! Don't worry about the training process that much, such as overfitting.*
 
 
 ```

README.md

@@ -5,7 +5,7 @@
 
 This is a short introduction on methods to use neural networks in an offensive manner (bug hunting, shellcode obfuscation, etc.) and how to exploit neural networks found in the wild (information extraction, malware injection, backdooring, etc.).
 
-Most of the methods presented are accompanied by an exercise found in this repo. The full article can be found here as well in the 'Article.pdf' file here or on arXiv at 
+Most of the methods presented are accompanied by an exercise found in this repo. The full article can be found here in '[Article.pdf](Article.pdf)' or on arXiv (uploaded soon). 
 
 
 ---
@@ -47,4 +47,6 @@ For instructions, please read the 'README.md' file in each of the exercise direc
 
 The neural networks found in the exercises are based on the examples provided by [keras](https://keras.io/). 
 
+Also check out Isao Takaesu's course on [Security and Machine Learning](https://github.com/13o-bbr-bbq/machine_learning_security/tree/master/Security_and_MachineLearning).
+
 If you find that there are errors or missing references, feel free to make a PR or contact me.