Every technical product is now incorporating machine learning at an explosive rate. But most people, even those with strong technical skills, don't understand how it works, what its capabilities are, and what security risks come with it. In this workshop, we'll make machine learning models using simple Python scripts, train them, and evaluate their value. Projects include computer vision, breaking a CAPTCHA, deblurring images, regression, and classification tasks. We will perform poisoning and evasion attacks on machine learning systems, and implement deep neural rejection to block such attacks.
No experience with programming or machine learning is required, and the only software required is a Web browser. We will use TensorFlow on free Google Colab cloud systems.
The quizzes are multiple-choice, online, and open-book. However, you may not ask other people to help you during the quizzes. You will need to study the textbook chapter
before the lecture covering it, and take the quiz before that class.
Each quiz is due 30 min. before class. Each quiz has 5 questions, you have ten minutes to take it, and you can make two attempts. If you take the quiz twice, the higher score counts.
Don't use CCSF's Canvas system for this class. Instead, all students
should use this Canvas server:
For class-related questions, please send messages inside Canvas or email
ml.sec.class@gmail.com
Schedule
Date
Due
Topic
Sat 8-19
1 The Machine Learning Landscape
OWASP Top Ten
Demo: ML 130
Sat 8-26
Quizzes Ch 1 and 2 Proj ML 130
2 End-to-End Machine Learning Project
Demo: ML 100
Sat 9-2
Holiday: No Class
Sat 9-9
Quiz Ch 3 Proj ML 100
3 Classification
Demo: ML 105
Sat 9-16
Quiz Ch 4 Proj ML 101 & ML 102
4 Training Models
Demo: ML 101, 102, 103
Sat 9-23
Quiz Ch 5 Proj Ml 103 & ML 104
5 Support Vector Machines
Sat 9-30
Quiz Ch 6 Proj Ml 105 & ML 106
6 Decision Trees
Sat 10-7
Quiz Ch 7 Proj Ml 107 & ML 108
7 Ensemble Learning and Random Forests
Sat 10-14
Quiz Ch 8 Proj Ml 109 & ML 110
8 Dimensionailty Reduction
Sat 10-21
Quiz Ch 9 Proj Ml 111 & ML 120
9 Unsupervised Learning Techniques
Sat 10-28
TBA
Sat 11-4
Quiz Ch 10 Proj Ml 121 & ML 122
10 Introduction to Artificial Neural Networks
Sat 11-11
Quiz Ch 11
11 Training Deep Neural Networks
Sat 11-18
Quiz Ch 12
12 Custom Models and Training with Tensorflow
Sat 11-25
Holiday: No Class
Sat 12-2
Quiz Ch 13
13 Loading and Preprocessing Data with Tensorflow
Sat 12-9
Last Class: TBA
Tue 12-12 through Tue 12-19
Final Exam available online throughout the week.
You can only take it once.
All Quizzes due 30 min. before class
Lectures
The Fundamentals of Machine Learning
1 The Machine Learning Landscape
KEY ·
PDF
OWASP Top 10 Machine Learning Security Risks ·
KEY ·
PDF OWASP Top 10 for LLM (PDF)
2 End-to-End Machine Learning Project
KEY ·
PDF
3 Classification
KEY ·
PDF
4 Training Models
KEY ·
PDF
5 Support Vector Machines
KEY ·
PDF
6 Decision Trees
KEY ·
PDF
7 Ensemble Learning and Random Forests
8 Dimensionailty Reduction
9 Unsupervised Learning Techniques
Neural Networks and Deep Learning
10 Introduction to Artificial Neural Networks
11 Training Deep Neural Networks
12 Custom Models and Training with Tensorflow
13 Loading and Preprocessing Data with Tensorflow
