CS 4301 - 0U3 Machine Learning in Cyber Security

Summer 2020

Location: JSOM 2.717
Time: Tuesday & Thursday 10:00AM - 12:15PM

Instructor: Wei Yang
Email: [email protected]
Office: ECSS 4.225
Office Hours: By Appointment

TA: TBD
Email: TBD
Office: TBD
Office Hours: TBD

This course is taught in both a seminar and a regular-course style. Each student will be expected to:

• Read and present research papers from the reading list (25 minutes presentation + 10-20 minutes Q&A) (30%)
• Perform an individual or group research project (30%)
• Quizzes (30%)
• Class Participation (10%)

Dive into Deep Learning
Building Intelligent Systems: A Guide to Machine Learning Engineering (using UTD email to access)
Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow (using UTD email to access)

Topic: Propose your own projects (Feel free to talk to the instructor about the proposed topic). A list of topics will be provided in the class.
Grading Policy:

• Proposal (5%)
• Midterm Report (5%)
• Midterm Demo (10%)
• Final Report (20%)
• Final Demo (10%)
• Project Document (10%)
• Project Website, README, Example subjects
• Code Evaluation (10%)
• Readability, Reusability
• Effectiveness Evaluation (30%)
• Evaluate based on the metrics proposed in the proposal.
• Level of difficulty will be taken into consideration (e.g., achieving or exceeding the state of the art).

Week	Dates	Topic
1.1	May. 26th	Course Content and Course Project [Slides] [Reading]
1-5		Machine Learning for Security
1.2	May. 28th	Security Analysis Foundation [Slides] [Reading1] [Reading2]
2.1	June. 2nd	Testing [Slides] [Reading1] [Reading2]
2.2	June. 4th	Fuzzing [Slides] [Video] [Reading1] [Reading2] [Reading3] [Reading4]
3.1	June. 9th	Machine Learning Basics[Slides] [Video] [Reading]
3.2	June. 11th	Automated Testing[Slides] [Reading1] [Reading2]
4.1	June. 16th	Automated Testing[Slides] [Reading1] [Reading2]
4.2	June. 18th	Symbolic Execution [Slides] [Reading1] [Reading2]
5.1	June. 23rd	ML for Code Analysis [Presentation1] [Reading1] [Reading2]
5.2	June. 25th	Analysis for ML Software [Presentation1] [Presentation2] [Reading]
TBD		Reinforcement Learning & Imitation Learning [Slides] [Reading]
6.1	June. 30th	Symbolic Execution (cont.) [Slides] [Presentation1] [Reading1] [Reading2]
TBD		Statistical Debugging & Web Vulnerability [Slides] [Reading]
6.2	July. 2nd	Embedding [Slides] [Reading]
7-10		Security for Machine Learning
7.1	July. 7th	Adversarial Machine Learning-Evasion Attacks [Slides] [Presentation1]
7.2	July. 9th	Adversarial Machine Learning-Other Attacks [Slides] [Reading]
7.1	July. 7th	Uncertainty of Machine Learning [Slides] [Reading] [Presentation1]
6.2	July. 2nd	Interpretability of Machine Learning [Slides] [Reading]
7.2	July. 9th	Poisoning Attack [Slides] [Reading]
8.1	July 14th	Privacy of Machine Learning [Slides] [Reading]
8.2	July 16th	Fairness of Machine Learning [Slides] [Reading]
9.1	July 21st	Testing of Machine Learning Models [Slides] [Reading]
9.2	July 23rd	Debugging of Machine Learning Models [Slides] [Reading]
10.1	July 28th	Detecting Issues in Deep Learning Applications [Slides] [Reading]
10.2	July 30th	Trending Security Topics [Slides] [Reading]
11.1	August 4th	Project Presentation [Slides] [Reading]