update assignment 4

assignments/tex/assignment_4.tex

@@ -32,13 +32,13 @@
 
 \maketitle
 
-\noindent In Assignment 4, you will work with your group to ``red-team'' your best model following the instructions below and treating your best model as a black box. A \href{https://nbviewer.jupyter.org/github/jphall663/GWU_rml/blob/master/assignments/assignment_4/assign_4_template.ipynb?flush_cache=true}{template} has been provided with examples of simple model extraction and adversarial example attacks. For those of you who use Python virtual environments, a basic \href{https://github.com/jphall663/GWU_rml/blob/master/assignments/requirements.txt}{\texttt{requirements.txt}} file is also available for the template.\\
+\noindent In Assignment 4, you will work with your group to ``red-team'' your best model following the instructions below and treating your best model as a black box. A \href{https://nbviewer.jupyter.org/github/jphall663/GWU_rml/blob/master/assignments/assignment_4/assign_4_template.ipynb?flush_cache=true}{template} has been provided with examples of simple model extraction and adversarial example attacks. \\
 
 \noindent Please let me know immediately if you find typos or mistakes in this assignment or related materials. 
 
 \section{Conduct a white-hat model extraction attack.}
 
-Cells 10--16 demonstrate a simple, but effective, model extraction attack. My example model extraction attack uses a single decision tree, that I then plot and use to craft adversarial examples. Please conduct a decision tree extraction attack, but you don't have to use my code. (Getting \texttt{graphviz} installed could be difficult for some, so feel free to use your favorite kind of decision tree if the template code proves difficult to run. Basic instructions for installing \texttt{graphviz} are available in resources associated with the \href{https://github.com/jphall663/GWU_rml/blob/master/py3.6_local_install.md}{class website}.)\\
+Cells 10--16 demonstrate a simple, but effective, model extraction attack. My example model extraction attack uses a single decision tree, that I then plot and use to craft adversarial examples. Please conduct a decision tree extraction attack, but you don't have to use my code. (Getting \texttt{graphviz} installed could be difficult for some, so feel free to use your favorite kind of decision tree if the template code proves difficult to run.)\\
 
 \noindent You may call \texttt{predict()} on your best model only one time to perform the extraction attack.
 
@@ -54,9 +54,9 @@ \section{Submit Code Results.}
 
 \noindent In the real world, after performing this red-teaming exercise, you would want to contact your manager and your organization's IT security team to discuss any discovered vulnerabilities. Countermeasures to discuss with business and IT colleagues may relate to authentication on the vulnerable model API endpoint, throttling/rate-limiting of the vulnerable model API and monitoring the model's production scoring queue for random data and training data, if possible.\\
 
-\noindent \textbf{Your deliverables are due Wednesday, June 21\textsuperscript{st}, at 11:59 PM ET.}\\
+\noindent \textbf{Your deliverables are due XX, XX XX\textsuperscript{XX}, at 11:59 PM ET.}\\
 
-\noindent Note that you may also improve Assignment 1 or 3 scores throughout the Summer I Session to improve your ranking, your Assignment 1 grade, your Assignment 3 grade, and your final project grade. Moving forward, you'll need to be able to show that your new predictions preserve AIR $>$ 0.8 for all protected groups.
+\noindent Note that you may also improve Assignment 1 or 3 scores to improve your ranking. Moving forward, you'll need to be able to show that your new predictions preserve AIR $>$ 0.8 for all protected groups.
 
 \end{document}