Securing AI and Advanced Topics

Securing AI and Advanced Topics

This course is part of AI for Cybersecurity Specialization

Instructor: Lanier Watkins

Access provided by UNext Learning

1,981 already enrolled

6 modules

Gain insight into a topic and learn the fundamentals.

17 reviews

Intermediate level

Recommended experience

2 weeks to complete

at 10 hours a week

Flexible schedule

Learn at your own pace

6 modules

Gain insight into a topic and learn the fundamentals.

17 reviews

Intermediate level

Recommended experience

2 weeks to complete

at 10 hours a week

Flexible schedule

Learn at your own pace

What you'll learn

Learn to implement AI-based solutions to detect and prevent credit card fraud in cloud environments.
Explore the fundamentals of Generative Adversarial Networks and their applications in generating synthetic data.
Gain hands-on experience with black-box and white-box adversarial attacks to assess and enhance model resilience.
Master techniques in feature engineering and performance evaluation to optimize AI models for cybersecurity applications.

Skills you'll gain

Tools you'll learn

Details to know

Shareable certificate

Add to your LinkedIn profile

Assessments

15 assignments

Taught in English

See how employees at top companies are mastering in-demand skills

Learn more about Coursera for Business

logos of Petrobras, TATA, Danone, Capgemini, P&G and L'Oreal

Build your subject-matter expertise

This course is part of the AI for Cybersecurity Specialization

When you enroll in this course, you'll also be enrolled in this Specialization.

Learn new concepts from industry experts
Gain a foundational understanding of a subject or tool
Develop job-relevant skills with hands-on projects
Earn a shareable career certificate

There are 6 modules in this course

In the course "Securing AI and Advanced Topics", learners will delve into the cutting-edge intersection of AI and cybersecurity, focusing on how advanced techniques can secure AI systems against emerging threats. Through a structured approach, you will explore practical applications, including fraud prevention using cloud AI solutions and the intricacies of Generative Adversarial Networks (GANs). Each module builds upon the previous one, enabling a comprehensive understanding of both offensive and defensive strategies in cybersecurity.

What sets this course apart is its hands-on experience with real-world implementations, allowing you to design effective solutions for detecting and mitigating fraud, as well as understanding adversarial attacks. By evaluating AI models and learning reinforcement learning principles, you will gain insights into enhancing cybersecurity measures. Completing this course will equip you with the skills necessary to address complex challenges in the evolving landscape of AI and cybersecurity, making you a valuable asset in any organization. Whether you are seeking to deepen your expertise or enter this critical field, this course provides the tools and knowledge you need to excel.

This course provides a comprehensive exploration of AI-based solutions for credit card fraud detection, emphasizing the implementation and evaluation of advanced algorithms, including Generative Adversarial Networks (GANs). Students will gain practical experience in executing adversarial attacks and optimizing machine learning models, enhancing their ability to develop robust AI systems. Through hands-on projects, participants will synthesize knowledge to address real-world challenges in fraud detection and model resilience.

What's included

2 readings

In this module, we study the background of threats that prevent credit card fraud. Then, we investigate hands-on credit card fraud detection implementations. Also, we discuss metrics to evaluate the performance of credit card fraud detection algorithms.

What's included

2 videos3 readings3 assignments

2 videos Total 14 minutes

Credit Card Fraud Prevention with AI 4 minutes
Credit Card Fraud Prevention: IBM Watson Example 10 minutes

3 readings Total 65 minutes

Reading References 10 minutes
Reading References 10 minutes
Self-Reflective Reading: Understanding of AI Fraud Prevention Tools 45 minutes

3 assignments Total 90 minutes

Credit Card Fraud Threats and AI Prevention 15 minutes
Implementing and Evaluating IBM Watson for Fraud Detection 15 minutes
Fraud Prevention with Cloud AI Solutions 60 minutes

In this module, we study generative adversarial networks (GANs) background. Then, we investigate a hands-on GAN implementation and how it can be used to develop synthetic data likely indistinguishable from the real data.

What's included

2 videos3 readings3 assignments

2 videos Total 17 minutes

Introduction to Generative Adversarial Networks (GANs) 9 minutes
Getting to Know GANs 8 minutes

3 readings Total 70 minutes

Reading References 15 minutes
Reading References 10 minutes
Self-Reflective Reading: Research GANs 45 minutes

3 assignments Total 90 minutes

Fundamentals of Generative Adversarial Networks (GANs) 15 minutes
Hands-On GAN Implementation and Synthetic Data Generation 15 minutes
Introduction to Generative Adversarial Attacks (GANs) 60 minutes

In this module, we will discuss black and white-box adversarial attacks. Also, we will explore hands-on implementations of several adversarial attacks.

What's included

2 videos3 readings3 assignments1 ungraded lab

2 videos Total 18 minutes

Adversarial Attacks Explained 8 minutes
Hands-On Adversarial Attacks 9 minutes

3 readings Total 65 minutes

Reading References 10 minutes
Reading References 10 minutes
Self-Reflective Reading: GANs and Adversarial Attacks 45 minutes

3 assignments Total 90 minutes

Understanding Black-box and White-box Adversarial Attacks 15 minutes
Practical Implementation of Adversarial Attacks 15 minutes
GANs and Adversarial Attacks 60 minutes

1 ungraded lab Total 60 minutes

Practice Lab: Generating Synthetic QR Codes with the Trained Generator 60 minutes

In this module we will study reinforcement learning (RL) and how it can be used for adversarial attacks. Also, we will study data engineering techniques to optimize datasets to help improve ML model performance.