AI and Cyber Security: Attack and Defend
Course Outline
This course explores the intersection of AI and cybersecurity, starting with a foundational understanding of AI technologies such as machine learning, deep learning, and natural language processing, as well as their applications in various industries. The content delves into mitigating risks associated with AI adoption, including risk management and ethical considerations, and identifying vulnerabilities in AI systems.
The importance of integrating AI into security operations is covered through the use of AI for intrusion detection, threat intelligence, and automated incident response, as well as AI’s potential for transforming hacking techniques while highlighting AI-powered attacks and tools. The Course also emphasizes the need for aligning AI with common security frameworks and regulatory compliance, as well as exploring future trends such as federated learning, AI-powered cyber deception, quantum computing for AI, explainable AI, and AI-driven security automation.
AI and Cyber Security: Attack and Defend Benefits
-
In this course, you will:
- Explain the architecture and operation of AI technologies
- Assess the security, privacy, and ethical risks associated with adopting AI
- Identify and test vulnerabilities in AI systems
- Implement controls to secure and monitor AI systems
- Apply AI to strengthen cybersecurity operations and governance
-
Training Prerequisites
Attendees should have foundational knowledge in networking and cybersecurity.
-
Who should attend?
- Cybersecurity Professionals
- AI and Data Science Professionals
- IT Professionals
- Data Privacy and Compliance Officers
- Developers and Software Engineers
AI and Cyber Security: Attack and Defend Course Outline
Learning Objectives
Chapter 1: Architecture and Operation of AI
- Evolution of AI technology
- Applying AI in Security
- Machine Learning
- Deep Neural Networks
- Federated Learning
- CNN, RNN, RvNN, Transformers
- NLP, LLM
- Generative AI
- LAB: Utilizing a Small Language Model
Chapter 2: Risk in Adopting AI
- Risk in Security
- Risks of AI Implementations
- Ethical Considerations
- Google Secure AI Framework
- Risks With GenAI
- Zero Trust Generative AI
- Protecting From GenAI aided attacks
- Mitigating AI Risks
- LAB: Deidentify GenAI Responses
Chapter 3: Attacking AI Vulnerabilities
- AI Algorithms, Data Sets, Models
- OWASP AI Security Risks
- Prompt Engineering
- AI vulnerabilities
- Attacks Against Classifiers
- NIST Adversarial ML Taxonomy
- Adversarial ML Threat Matrix
- AI Red Teaming
- LAB: Penetration Testing an AI System
Chapter 4: Securing AI
- Mitigating AI Risks
- GenAI Monitoring and Logging
- AI Gateways
- Agent Gateways
- AI Security checklist
- LAB: Safeguarding With Gemini AI
Chapter 5: AI-Powered Hacking
- Using AI to Hack
- GenAISocial Engineering
- Deepfakes
- AI infused Hacking
- Long Con AI
- LAB: Enhance Hacking With GenAI
Chapter 6: Defending Security Operations with AI
- SecOps
- AI-Based Security Processes
- IT Operations and Cloud AI
- GenAIRed Teaming
- AI Security Tools
- Google AI SecOps
- Cybersecurity Copilot
- LAB: Analyze a Codebase With Gemini
- LAB: SecOps Threat Hunting With AI
- LAB: Anatomy of an AI Model Attack
- LAB: Secure Coding With AI
Chapter 7: Regulating AI Governance
- Regulatory Compliance for AI
- NIST AI Risk Management Framework
- OWASP Security & Governance Checklist
- Responsible AI
- GenAI Governance Framework
- choosing a selection results in a full page refresh