CPTEnglishBeginner· AI Security, Cybersecurity, Machine Learning

AI Under Attack: Adversarial Inputs, Prompt Injection, and Model Security

Master the art of defending AI systems against adversarial attacks and manipulation

1h 30 lessons

What you'll learn

Identify the unique vulnerabilities that distinguish AI models from traditional, deterministic software.
Analyze how adversarial inputs and small perturbations can force unintended model behavior.
Explain the mechanics behind training data poisoning and strategies for maintaining data provenance.
Evaluate the risks associated with prompt injection and unauthorized tool execution in AI agents.
Apply defensive design patterns to secure the entire AI development and deployment lifecycle.
Detect hidden backdoors, latent triggers, and sleeper behaviors engineered into models.
Implement robust monitoring systems to identify abnormal model behavior and potential security incidents.

About this course

Artificial intelligence is no longer just software; it is a fundamental pillar of modern infrastructure, from finance and healthcare to autonomous systems. As AI systems grow in complexity, they introduce a distinct, expansive attack surface that traditional cybersecurity measures—like firewalls and encryption—cannot fully mitigate. This course provides a deep dive into the unique threats facing modern models, including adversarial inputs, data poisoning, model theft, and prompt injection.

Learners will examine why AI is uniquely susceptible to manipulation and how these vulnerabilities differ from conventional software bugs. We will cover the entire AI lifecycle, from initial training data collection and fine-tuning to deployment and integration with external tools. Through a rigorous, architecture-centric approach, this course demonstrates how to move beyond basic safety features to implement comprehensive defensive architectures that prioritize robustness, provenance, and controllability.

Key areas of focus include:

Training-time security and data integrity.
Inference-time defenses against real-world adversarial probes.
Detecting hidden backdoors and sleeper behaviors in model weights.
Securing physical-world sensors against environmental spoofing.

Curriculum · 30 lessons

1:02:15.2 of content

1.
Understanding the Critical Need for Securing Artificial Intelligence Systems
FREE
2:00.3
2.
Identifying Unique Cybersecurity Challenges Posed by Modern AI Models
FREE
1:56.7
3.
Differences Between Traditional Software Security and AI Model Security
FREE
1:59.5
4.
Foundational Principles for Securing AI Systems and Data Infrastructure
1:59.8
5.
Mapping the Expanded Attack Surface of Modern AI Ecosystems
2:07.1
6.
Securing the AI Lifecycle from Development to Deployment and Integration
2:03.9
7.
Mitigating Risks of Training Time Attacks and Data Contamination
1:58.1
8.
Implementing Data Provenance and Quality Controls to Prevent Poisoning
2:10.5
9.
Detecting Hidden Backdoors and Sleeper Behaviors in AI Models
2:06.0
10.
Managing Inference Time Risks and Adversarial Inputs During Deployment
2:06.8
11.
Understanding the Mechanics and Dangers of Adversarial Machine Learning
1:56.5
12.
Addressing Model Vulnerability to Small Perturbations and Input Manipulations
2:07.6
13.
Securing AI Against Physical World Adversarial Attacks and Sensor Spoofing
2:07.4
14.
Achieving Robustness in AI Systems Against Intentional Adversarial Probing
2:08.3
15.
Implementing Effective Red Teaming and Adversarial Testing Strategies
2:08.9
16.
Addressing Prompt Injection Risks in Large Language Model Architectures
1:55.3
17.
Differentiating Between Direct and Indirect Prompt Injection Vulnerabilities
2:01.1
18.
Securing AI Assistants Connected to Sensitive Enterprise Data Sources
2:04.7
19.
Managing Security Risks Associated with Autonomous AI Agent Tool Use
2:02.1
20.
Resolving Instruction Hierarchy Conflicts to Maintain System Control
2:03.2
21.
Preventing Model Extraction Attacks and Protecting Proprietary AI Assets
2:05.7
22.
Addressing Privacy Leakage and Data Memorization in Trained AI Models
1:57.0
23.
Securing Software Development Pipelines Against AI-Generated Code Vulnerabilities
2:09.9
24.
Managing Supply Chain Risks in Complex AI System Deployments
2:13.0
25.
Addressing Security Challenges in Multimodal and Embodied AI Systems
2:08.2
26.
Implementing Defense in Depth Strategies for Probabilistic AI Architectures
2:05.9
27.
Designing Secure Architectures to Isolate AI from Critical Infrastructure
2:00.8
28.
Establishing Standards and Accountability for Trustworthy AI Deployment
2:13.9
29.
Navigating Ethical and Governance Decisions in High-Stakes AI Adoption
2:09.1
30.
The Strategic Importance of Securing AI as Critical Infrastructure
2:08.0

Requirements

A foundational understanding of cybersecurity principles and risk management.
Basic familiarity with how machine learning models and neural networks are trained.
Interest in AI safety, security architecture, or system reliability.
Comfort with high-level technical discussions regarding software development and data pipelines.

Certificate of Completion

Complete this course to earn a verifiable Certificate of Completion for your CPT training record. Here's how:

1Watch all the lessons — work through every lesson in the curriculum. Each completed lesson brings your progress closer to 100%.
2Pass all the quizzes — score 70% or higher in each quiz within the course. Quizzes are part of the curriculum and must be passed to finish.
3Download your certificate — once you reach 100% progress, download a personalised Certificate of Completion showing your name, the CPT hours earned, and your quiz score.

Sample certificate: