Apprentice
|
Adversarial ML & Security Threats
|
Module 2: Attacks Against ML Models

Module 2: Attacks Against ML Models

by NSTC

February 24, 2026

About Module 2: Attacks Against ML Models

Module Content

Module 2: Attacks Against ML Models

12 Lessons

Chapter 2.1: Evasion Attacks on Image, Text, and Tabular Models

Lesson 1: Lesson 2.1.1 Techniques for crafting image-specific attacks (e.g., FGSM, PGD)

Lesson 2: Lesson 2.1.2 Text-based attacks and strategies to evade detection

Lesson 3: Lesson 2.1.3 Attacks targeting tabular data and their impact

Chapter 2.2: Poisoning Attacks During Training

Lesson 1: Lesson 2.2.1 Types of poisoning attacks and their motivations

Lesson 2: Lesson 2.2.2 Crafting poison attacks on training data

Lesson 3: Lesson 2.2.3 Countermeasures for defending against poisoning

Chapter 2.3: Model Inversion and Membership Inference

Lesson 1: Lesson 2.3.1 Techniques for model inversion

Lesson 2: Lesson 2.3.2 Practical implications of membership inference

Lesson 3: Lesson 2.3.3 Defense mechanisms against these attacks

Chapter 2.4: Tools and Libraries (Foolbox, ART, CleverHans)

Lesson 1: Lesson 2.4.1 Introduction to Foolbox for adversarial attack implementation

Lesson 2: Using ART for attack and defense strategies

Lesson 3: CleverHans and its role in adversarial ML

Comments are closed.