The AI Horizon
Learn /Adversarial ML & AI Model Security

Adversarial ML & AI Model Security

14 curated resources for this skill.

Coursera AI Security Fundamentals

Course Beginner Free

Introductory course covering AI security basics and common vulnerabilities.

FedLearn Security & Adversarial AI Course

Course Expert Free

Advanced course on federated learning security and privacy-preserving ML.

HiddenLayer Adversarial ML Training

Training Intermediate Paid

Specialized training on advanced adversarial ML techniques and defenses.

NVIDIA Deep Learning Institute - Adversarial ML

Course Beginner Free

Free course on adversarial machine learning concepts and defense strategies.

OWASP Top 10 LLM, Updated 2025: Examples & Mitigation (Oligo Academy)

Article Intermediate Free

Vendor-backed guide to each OWASP Top 10 for LLM Applications with examples and mitigations.

Cloud Computing for Machine Learning

Playlist Intermediate Free

GCP playlist for secure MLOps and model protection

MLSecOps in Practice

Video Intermediate Free

Implementing MLSecOps for AI system security.

Splunk Adversarial ML Learning Resources

Resource Intermediate Free

Comprehensive resources on adversarial machine learning and detection methods.

A Probably Private Mini-Course: Introduction to AI/ML Security

Course Beginner Free

YouTube mini-course and GitHub repo introducing AI/ML security fundamentals: red teaming basics and adversarial ML.

Hack The Box: AI Data Attacks

Lab Intermediate Free

Hands-on course covering adversarial attacks on AI data pipelines with practical lab exercises.

Hands-On AI Security and Red Teaming (YouTube)

Playlist Beginner Free

Hands-on introduction to AI/ML security topics with a companion GitHub repository -- attacking local models and learning different vulnerability types.

OWASP LLM Prompt Injection Prevention Cheat Sheet

Guide Intermediate Free

Comprehensive guide to defending against prompt injection attacks (OWASP #1 LLM risk).

Protect AI: MLSecOps Foundations Course

Certification Intermediate Free

Free four-part MLSecOps curriculum (20 bite-sized modules) for AI users, developers, and security teams.

TryHackMe: AI/ML Security Threats Room

Lab Beginner Free

Free interactive room covering AI/ML security fundamentals including prompt injection, AI-driven phishing detection, and LLM vulnerabilities.