CompTIA SecAI+

Participants should have:

• basic knowledge of computer networks and operating systems,
• basic orientation in cybersecurity,
• knowledge at the level of CompTIA Security+, CySA+, or equivalent experience is recommended,
  approximately 2 years of experience in cybersecurity.

1. AI Fundamentals in Cybersecurity
• Artificial intelligence, machine learning, and deep learning
• Generative AI
• Large Language Models (LLM)
• Small Language Models (SLM)
• Natural Language Processing (NLP)
• Generative Adversarial Networks (GAN)
• Transformers
• Current trends of AI in cybersecurity
• Practical use of AI in enterprise environments
2. Machine Learning and the AI Lifecycle
• Supervised Learning
• Unsupervised Learning
• Reinforcement Learning
• Model training
• Testing and validation of models
• Model fine-tuning
• Epochs, pruning, and quantization
• AI Development Lifecycle
• Model monitoring
• Human-in-the-loop
3. Data Security and Prompt Engineering
• Types of data used for AI
• Data lineage
• Data provenance
• Data integrity
• Data quality management
• Prompt engineering
• Zero-shot prompting
• One-shot prompting
• Multi-shot prompting
• Prompt templates
• Prompt injection attacks
• Protection of generative AI systems
4. AI Architecture and Components
• AI models
• AI agents
• AI services
• API interfaces
• Embeddings
• Retrieval-Augmented Generation (RAG)
• Vector databases
• Enterprise AI architectures
• Integrating AI into enterprise applications
5. Securing AI Systems
• AI attack surface
• Secure AI architecture
• Identity and Access Management (IAM)
• Least privilege
• Segregation of duties
• API security
• Secrets management
• Data encryption
• Protection of training data
• Protection of models
• Protection of inference services
6. AI Threats and Attacks
• Prompt injection
• Jailbreaking AI models
• Data poisoning
• Model poisoning
• Adversarial machine learning
• Membership inference attacks
• Model extraction
• Model theft
• Data leakage
• Hallucinations
• Supply chain attacks against AI solutions
7. Secure AI Development and MLOps
• Secure SDLC
• DevSecOps for AI environments
• MLOps
• CI/CD pipeline for AI
• Model governance
• Security testing
• AI model validation
• Monitoring AI systems
8. AI-Assisted Security Operations
• AI in the Security Operations Centre (SOC)
• AI for SIEM tools
• Correlation of security events
• Automation of security processes
• Threat hunting using AI
• Prioritization of security incidents
• AI-assisted security analytics
9. AI for Incident Response
• AI-assisted triage
• Log analysis using AI
• Root Cause Analysis
• Automated incident investigation
• Malware analysis
• Forensic analysis
• Automation of incident response
10. Vulnerability Management and Threat Intelligence
• Prioritization of vulnerabilities
• Risk scoring
• Exposure analysis
• Asset discovery
• Threat intelligence
• IOC analysis
• TTP correlation
• MITRE ATT&CK framework
• Predictive threat analysis
11. AI Governance and Responsible AI
• Governance frameworks for AI
• Responsible AI
• Explainability
• Transparency
• Accountability
• AI Ethics
• Organizational policies
• AI lifecycle management
12. AI Risk Management and Compliance
• Risk Assessment
• AI Risk Register
• Risk Treatment
• Business Impact Analysis
• Audit of AI solutions
• NIST AI Risk Management Framework
• ISO/IEC 42001
• GDPR and AI
• EU AI Act
• Compliance requirements for AI solutions
13. Certification Exam Preparation
• Overview of certification domains
• Question types
• Performance-Based Questions (PBQ)
• Practical scenarios
• Practice tests
• Exam Tips & Tricks
• Final review

The course includes lab exercises focused on:

• analyzing AI security risks,
• designing a secure AI architecture,ň
• protecting models and datasets,
• detecting and mitigating AI attacks,
• AI support for security operations,
• AI-assisted threat hunting,
• AI governance and risk assessment,
  solving scenarios similar to the certification exam.

The course prepares participants for the CompTIA SecAI+ (CY0-001) exam

Exam domains:

• Basic AI Concepts Related to Cybersecurity – 17 %
• Securing AI Systems – 40 %
• AI-Assisted Security – 24 %
• AI Governance, Risk and Compliance – 19 % [examsdigest.com], [onlc.com]