Connected & Automated Vehicles Course

Adversarial Machine Learning

Start Anytime
$250
Register

Location:

Online

Schedule:

Self-paced

Course Summary

Learning Objectives

Course Overview

Credentials

Instructional Team

Course Summary

Discounts

The following GoBlue pricing discounts are available and cannot be combined. Please contact us at [email protected] for a promotional code that will allow you to apply the eligible discount to your registration.

With 15 or more enrollments, you may want to consider a custom program for your organization. Please contact us to learn more about our partnership opportunities.

Once you have paid, a discount cannot be added retroactively.

THESE DISCOUNTS ARE NOT APPLICABLE FOR PARTNER PROGRAMS.

Name Details Level
Group Discount Level 1 Enroll 3-4 participants in one course offering. 5%
Group Discount Level 2 Enroll 5 or more participants in one course offering. 10%
U.S. Government Current employees with .gov email (not applicable to government contractors). 10%
U.S. Military Active duty personnel, reservists, retired or disabled veterans. 10%
Students Currently enrolled student from any university; please send photo of date-stamped student ID. 10%
Michigan Engineering Professional Education Alumni Past participants of any Michigan Engineering Professional Education certificate course. 10%
U-M Alumni U-M alumni from any school or department – please send uniqname to [email protected] for confirmation. 20%
U-M Students and Staff Current U-M students, faculty, and staff – please send uniqname to [email protected] for confirmation. 20%
Go Blue Discounts
Instruction Time Completion Time CEUs
Adversarial Machine Learning ~ 4-6 hours 60 days after start date 1

Adversarial Machine Learning has profound implications for safety-critical systems that rely on machine learning techniques, like autonomous driving. Machine learning models, such as neural networks, are often not robust to adversarial inputs. This course introduces concepts from machine learning and then discusses how to generate adversarial inputs for assessing robustness of machine learning models. Potential defenses — and their limits — are also discussed.

Learning Objectives

  • Understand why robustness of machine learning models is important in different application contexts, including autonomous driving
  • Understand different types of attacks on machine learning systems
  • Machine learning concepts review: regression, loss, model training goals, gradient descent, and classification
  • Understand attack strategies on machine learning systems by modifying inputs
  • Understand different types of defenses and their limits

Course Overview

  • Introduction (5 min)
  • Adversarial Machine Learning Overview (21 min)
  • Adversarial Attacks on Machine Learning Models (8 min)
  • Physical Attacks on Machine Learning Models (32 min)
  • Short Intro to (Non-Adversarial) Machine Learning (18 min)
  • Types of Machine Learning Problems: Regression and Classification (8 min)
  • Linear Regression: Training and Loss (20 min)
  • Linear Regression: Model Fitting Using Gradient Descent (34 min)
  • Classification (18 min)
  • Neural Networks (29 min)
  • Adversarial Attacks on Neural Networks (41 min)
  • Advanced Attacks (32 min)
  • Physical-World Adversarial Attacks (22 min)
  • Defenses: Making Models Robust Against Adversarial Attacks on Neural Networks (32 min)
  • You will have access to this course for 60 days.
  • This course contains 4-6 hours of required recorded material and an associated testing assessment.

Successful completion requires you to receive an 70% passing grade on the course assessment.

There are no prerequisites for this course. A bachelor’s degree in a science, engineering, or technical field is recommended, but not required.

View Technical Requirements

Administrative/Online Technical Support
Support staff are available via phone and email to help with administrative and technical issues during our normal business hours (Monday through Friday 8:00 a.m. to 5:00 p.m. Eastern Time). 

Content Questions/Certification Project Support
Candidates are welcome to contact the course instructors for content questions and project support. The instructors will provide support via email, phone consultation, and/or online videoconferencing.

Credentials

Powered by: 

Digital Badge

Digital badge earned after successful completion of this course.

Instructional Team

Atul Prakash, PhD

  • Professor, Electrical and Computer Science

What's next?

Design & Innovation
Course

Organizational Design

Leadership
Course

Transformative Leadership

Get Started

For more information or answers to any questions please email [email protected] or fill out the form.

Main Office:
2401 Plymouth Road, Suite A/B
Ann Arbor, MI 48105
(734) 647-7200
[email protected]

Linkedin Instagram Youtube

MICHIGAN ENGINEERING ONLINE & PROFESSIONAL EDUCATION

ONLINE DEGREES

PROFESSIONAL EDUCATION

© 2025 The Regents of the University of Michigan