Certified Offensive AI Security Professional (COASP)

Price
$2,995.00 USD

Duration
5 Days

Delivery Methods
Virtual Instructor Led
Private Group

Request More Information

Download Course Details

Course Details Only
Course Details & Schedule

Skip to Class Dates

Who Should Attend?

Penetration Testers / Ethical Hackers, Red Team / Offensive Security Specialists, Security Engineers / DevSecOps Engineers, SOC Analysts / Incident Responders, AI/ML Engineers focused on security

Top-rated instructors: Our crew of subject matter experts have an average instructor rating of 4.8 out of 5 across thousands of reviews.
Authorized content: We maintain more than 35 Authorized Training Partnerships with the top players in tech, ensuring your course materials contain the most relevant and up-to date information.
Interactive classroom participation: Our virtual training includes live lectures, demonstrations and virtual labs that allow you to participate in discussions with your instructor and fellow classmates to get real-time feedback.
Post Class Resources: Review your class content, catch up on any material you may have missed or perfect your new skills with access to resources after your course is complete.
Private Group Training: Let our world-class instructors deliver exclusive training courses just for your employees. Our private group training is designed to promote your team’s shared growth and skill development.
Tailored Training Solutions: Our subject matter experts can customize the class to specifically address the unique goals of your team.

Learning Credits: Learning Credits can be purchased well in advance of your training date to avoid having to commit to specific courses or dates. Learning Credits allow you to secure your training budget for an entire year while eliminating the administrative headache of paying for individual classes. They can also be redeemed for a full year from the date of purchase. If you have previously purchased a Learning Credit agreement with New Horizons, you may use a portion of your agreement to pay for this class.

If you have questions about Learning Credits, please contact your Account Manager.

Corporate Tech Pass: Our Corporate Tech Pass includes unlimited attendance for a single person, in the following Virtual Instructor Led course types: Microsoft Office, Microsoft Technical, CompTIA, Project Management, SharePoint, ITIL, Certified Ethical Hacker, Certified Hacking Forensics Investigator, Java, Professional Development Courses and more. The full list of eligible course titles can be found at https://www.newhorizons.com/eligible.

If you have questions about our Corporate Tech Pass, please contact your Account Manager.

Course Prerequisites

Strong technical background recommended, Requires: 2–3 years of cybersecurity experience, with understanding of security operations, networks or application security and offensive security experience

Agenda

Module 01: Offensive AI and AI System Hacking Methodology

AI & ML Fundamentals
AI Attack Surface and Threat Landscape (ATLAS-Aligned)
AI Attack Taxonomy and Classification
OWASP LLM and ML Top 10 (2025) – Overview & Mapping
AI System Hacking Methodology
Securing AI Systems – Foundations (Defensive Anchor)
AI Security Governance and Compliance

Module 02: AI Reconnaissance and Attack Surface Mapping

OSINT for AI Assets
Tools and Techniques for AI OSINT
Data & Training Pipeline Intel Gathering
Mapping AI Attack Surfaces from OSINT
Discovering AI Endpoints & Services
AI API & Parameter Enumeration
Model & Vector Store Enumeration
Defensive – Reducing AI OSINT Exposure
Defensive – Hardening Enumerated Surfaces
AI Threat Intelligence & Continuous Monitoring

Module 03: AI-Specific Vulnerability Scanning and Fuzzing

Fundamentals of AI Vulnerability Assessment
Tools and Techniques for Vulnerability Scanning
Fuzzing Techniques for AI Systems
Defensive – Integrating Scanning & Fuzzing

Module 04: Prompt-Based and LLM Application Attacks

LLM Architecture & Trust Boundaries
Prompt Injection & Jailbreaking
Sensitive Information Disclosure and System Prompt Leakage
Improper Output Handling and Misinformation
Advanced Prompt Attack Techniques
Defensive – Secure LLM Application Design

Module 05: Adversarial Machine Learning and Model Privacy Attacks

Adversarial ML Attacks
Practical Adversarial Input Attacks
Privacy & Model Extraction Attacks
Evaluating Robustness & Trustworthiness
Emerging Model Attack Techniques
Defensive – Privacy & Robustness Mitigations

Module 06: Data and Training Pipeline Attacks

Understanding AI Data & Training Pipelines
Data Poisoning Attacks
Backdoor / Trojan Attacks in Training Pipelines
AI Supply Chain Attack Vectors
Defensive – Securing Data & Training Pipelines

Module 07: Agentic AI and Model-to-Model Attacks

Agentic AI Architecture & Attack Surface
Excessive Agency & Autonomy
Model-to-Model and Cross-LLM Attacks
Unbounded Consumption and Denial of Wallet
AI Workflow and Orchestration Attacks
Defensive – Securing Agentic Applications

Module 08: AI Infrastructure and Supply Chain Attacks

AI Infrastructure & Integration Landscape
System and Framework Exploits
Tool and API Abuse in AI Apps
Supply Chain Threats (Deep Dive)
Defensive – Hardening AI Infra & Supply Chain

Module 09: AI Security Testing, Evaluation, and Hardening

AI Security Test & Evaluation Fundamentals
Designing AI Security Test Plans
Executing AI Security Tests
Reporting, Assurance & Risk Management
Defensive – Embedding T&E into MLOps/DevSecOps

Module 10: AI Incident Response, Forensics, and Capstone Red Team

Detecting & Responding to AI-Specific Incidents
Logging, Telemetry & Evidence Collection
AI Forensics & Post-Incident Analysis
Capstone: Full-Scope AI Red Team Engagement
Course Wrap-Up & Professional Practice

Get in touch to schedule training for your team
We can enroll multiple students in an upcoming class or schedule a dedicated private training event designed to meet your organization’s needs.