Self-paced Course: Coming soon

Practical AI Security: Attacks, Defenses, and Applications

Practical AI Security: Attacks, Defenses, and Applications takes you from the foundations of machine learning to advanced security practices involving generative AI and large language models. Through hands-on labs, you’ll train models, build LLM-based apps, and simulate real red team attacks. You’ll explore both offensive and defensive AI applications — from automated pentesting agents and exploit discovery to threat modeling, code review, and guardrail design. Along the way, you’ll work with tools like Scikit-Learn, Hugging Face, and FAISS, and learn frameworks such as Google’s SAIF and MITRE ATLAS. By the end, you’ll walk away with practical code, reusable tools, and a solid grasp of how to attack and defend AI systems in real-world environments.
  • Level

    Beginner / Intermediate

  • Video

    12 hours - 96 videos

  • CERTIFICATION EXAM

    Included

A path to CAISR (Certified AI Security Researcher) certification

Key Objectives

  • Understand the core concepts distinguishing AI, Machine Learning, and Deep Learning, including the complete ML model training lifecycle.
  • Gain hands-on experience with Neural Networks, from basic forward propagation to training models on datasets like MNIST.
  • Master the fundamentals of LLMs, including Transformer architecture, tokenization (BPE), context windows, and embeddings.
  • Become proficient in Prompt Engineering (zero-shot, few-shot, Chain-of-Thought) and controlling model output via sampling parameters (Temperature, Top-k, Top-p).
  • Learn to use essential tools like Hugging Face, Scikit-Learn, and vector databases like FAISS.
  • Build and deploy AI applications, including custom RAG (Retrieval-Augmented Generation) systems and simple web apps.
  • Develop Offensive AI capabilities, including building AI agents for pentesting, vulnerability scanning, and exploit development assistance.
  • Implement Defensive AI and DevSecOps strategies, such as automating threat modeling, patch diffing, and security code reviews.
  • Analyze and execute attacks against AI systems, including Prompt Injection, agent exploitation, and data exfiltration techniques.
  • Apply AI to enhance Reverse Engineering workflows with tools that integrate AI into Ghidra and Binary Ninja.
  • Understand and implement AI security best practices and frameworks, including Google’s Secure AI Framework (SAIF) and red teaming methodologies for LLMs.
  • Analyze real-world AI vulnerabilities and CVEs in popular frameworks and applications like LangChain and GitHub Copilot.

Who Should Attend?

This course is ideal for anyone interested in learning about the application of AI in cybersecurity.

Prerequisites

To successfully participate in this course, attendees should possess the following:
  • Working knowledge of cybersecurity and pentesting fundamentals
  • Basic understanding of Artificial Intelligence and Machine Learning fundamentals
  • Understanding of principles of data science and learning algorithms
  • Understanding of fundamental programming concepts and looping structures in at least one higher-level language used in machine learning (eg: Python, or similar)

Duration

  • 365 days of access after purchase

Technical Requirements

  • Laptop with 8+ GB RAM and 40 GB hard disk space
  • Administrative access on the system

Syllabus

START LEARNING

Practical AI Security: Attacks, Defenses, and Applications

On-demand
  • Immediate access to materials
  • Lecture recordings and self-assessments
  • 365 days of access
  • Certification of course completion
  • Dedicated email support

Enroll a group

Get in touch for pricing
Includes everything from the individual rate, plus:
  • Special group pricing
  • Available add-ons to Oversee and track individual student progress for large groups

Enterprise

Get in touch for pricing
Includes everything from the group rate, with the ability to manage multiple seats and track student progress across all courses. Contact us with your preferred courses and number of students for a customized quote.

Unlock Job Opportunities

Gain the in-demand skills to pursue career opportunities such as:

AI Security Engineer*

A Tech Giant Company

$136,000 – $212,800 a year

Required Qualifications

- Bachelor’s degree in Computer Science or a related field
- 2+ years of combined experience in areas such as threat modeling, secure coding practices, identity and access management, authentication, cryptography, or network security
- Familiarity with GenAI technologies and related security risks, along with mitigation strategies such as penetration testing and exploit development (or equivalent expertise)

Read more

Offensive AI Security Tester*

IT Services Provider Firm

$114,400 - $124,800 a year

Required Qualifications

- 5+ years of relevant professional experience
- Practical expertise in adversarial testing of GenAI systems (e.g., jailbreaks, prompt injections, input–output evaluations, data exfiltration) and delivering actionable mitigation steps

- Solid understanding of ML/GenAI concepts (LLMs, embeddings, diffusion models) and adversarial ML techniques (such as model extraction, data poisoning, and prompt manipulation)

Read more

Adversarial Prompt Expert*

IT Services Provider Firm

Up to $80 per hour, part time

Required Qualifications

- Extensive hands-on experience with LLMs, both open- and closed-source, and comfort experimenting across different platforms
- Strong background in prompt engineering and jailbreak techniques, including evasion strategies and innovative approaches to bypassing model safeguards
- Adversarial and security-oriented mindset, with additional value placed on red teaming or offensive security experience

Read more

*This is a compiled job description based on actual postings from LinkedIn and Indeed.

Created by

8kSec Academy

Our instructors are experts with over a decade of hands-on experience in mobile security, IoT exploitation, and vulnerability assessment. They've delivered numerous private trainings to high-profile clients and shared their knowledge at renowned conferences like BlackHat, Def Con, POC, TyphoonCon, Brucon, Hack in Paris, Phdays, Appsec USA, and more.

With thousands of students having completed our courses, our instructors continually refine their content based on real-world feedback. Whether through live sessions or our new on-demand courses, we ensure the same high-quality learning experience is accessible to professionals worldwide.