Securing AI and Advanced Topics

Johns Hopkins University via Coursera

Coursera based on 0 ratings

Likes

Overview

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...

Syllabus

Course Introduction

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.

Fraud Prevention with Cloud AI Solutions

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.

Introduction to Generative Adversarial Attacks (GANs)

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.

GANs and Adversarial Attacks

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

Reinforcement Learning

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 improve ML model performance.