AI for Cybersecurity Professionals

• Understand the application of AI, Machine Learning and Generative AI in cybersecurity.
• Use AI tools to support threat intelligence, security monitoring and incident detection.
• Apply AI to analyse security logs, alerts and network activity.
• Use AI to support incident response, investigation and digital forensics
• Apply AI-assisted techniques for vulnerability and cybersecurity risk assessment.
• Identify and analyse AI-enabled cyber threats, including phishing, social engineering and automated attacks.
• Understand and mitigate prompt injection, data poisoning, excessive agency and other LLM security risks.
• Apply MITRE ATT&CK, MITRE ATLAS, OWASP and NIST frameworks to AI-enabled cybersecurity activities.
• Develop secure and responsible AI practices for cybersecurity operations.
• Validate AI-generated security outputs and maintain appropriate human oversight
• Develop practical AI-assisted cybersecurity workflows, reports and incident-response playbooks

• Module 1: Foundations of Artificial Intelligence for Cybersecurity Artificial Intelligence, Machine Learning and Generative AI Large Language Models (LLMs) Predictive AI vs Generative AI AI agents and agentic AI How AI systems process cybersecurity inform
• Module 2: Generative AI for Cybersecurity Professionals Using ChatGPT, Gemini, Copilot and other AI assistants Cybersecurity-specific prompting Context engineering for security tasks Developing reusable security prompts AI-assisted security research Summa
• Module 3: AI-Assisted Threat Intelligence Fundamentals of Cyber Threat Intelligence (CTI) Strategic, operational, tactical and technical intelligence AI-assisted threat intelligence collection Analysing threat reports Extracting Indicators of Compromise (
• Module 4: AI for Security Operations Centres (SOC) Role of AI in modern SOCs AI-assisted alert triage Security event summarisation Alert prioritisation Incident correlation Reducing security-alert fatigue AI-assisted investigation Security Operations Cent
• Module 5: AI for Network Security Monitoring AI-assisted network traffic analysis Network anomaly detection Identifying suspicious communication patterns Detecting unusual network behaviour DNS and HTTP security analysis Authentication and access anomalie
• Module 6: AI for Endpoint and Log Analysis AI-assisted endpoint security Analysing Windows and Linux logs Event correlation Detecting suspicious processes Authentication-event analysis Privilege escalation indicators Persistence indicators Command-line ac
• Module 7: AI-Assisted Incident Response AI in the incident-response lifecycle Incident identification and classification Triage and investigation Evidence collection planning Incident timeline development Root-cause analysis Containment recommendations Er
• Module 8: AI for Vulnerability Management AI-assisted vulnerability identification Vulnerability intelligence CVE analysis Vulnerability prioritisation Exploitability assessment Asset-risk context Patch prioritisation Vulnerability remediation recommendat
• Module 9: AI for Phishing, Social Engineering & Email Security AI-assisted phishing detection Email-header analysis Suspicious URL analysis Social-engineering indicators Business Email Compromise (BEC) AI-generated phishing campaigns Deepfakes and synthet
• Module 10: AI for Malware Analysis Introduction to AI-assisted malware analysis Static versus dynamic analysis Analysing malware behaviour Extracting IoCs AI-assisted reverse-engineering support Suspicious code interpretation Malware family classification
• Part II — Securing Artificial Intelligence Module 11: AI Security Fundamentals Why AI systems create new cybersecurity risks AI attack surface AI models, data, applications and APIs AI supply-chain risks Model security Data security Application security
• Module 12: OWASP GenAI & LLM Security A dedicated section should cover the current OWASP GenAI security guidance rather than relying only on the older LLM Top 10. OWASP's active project now identifies the 2026 GenAI LLM Top 10 as its current release. To
• Module 13: Prompt Injection & AI Application Attacks Direct prompt injection Indirect prompt injection Jailbreaking concepts System-prompt manipulation Data exfiltration through prompts Malicious documents and web content Tool manipulation Agent hijacking
• Module 14: Securing RAG, Vector Databases & AI Agents Retrieval-Augmented Generation (RAG) RAG architecture Security of knowledge bases Vector databases Embedding security Access-control issues in RAG Data leakage Retrieval poisoning AI agent architecture
• Part III — AI-Powered Cyber Attacks Module 15: AI-Enabled Cyber Threats How attackers use Generative AI AI-assisted reconnaissance Automated social engineering AI-generated phishing Automated vulnerability research Malware development risks Credential a
• Module 16: MITRE ATLAS for AI Threat Modelling Introduction to MITRE ATLAS AI attack tactics and techniques AI-enabled attack lifecycle Threat modelling AI systems Mapping AI attacks to ATLAS AI red teaming Attack scenarios Defensive mitigations AI incide
• Part IV — AI Security Operations Module 17: AI-Assisted Digital Forensics AI in digital forensic investigations Evidence triage Log analysis Timeline analysis File and artefact classification Text and document analysis Threat-intelligence correlation AI
• Module 18: AI for Security Risk & Compliance AI-assisted cybersecurity risk assessments Identifying security gaps Risk prioritisation Control mapping Policy analysis Security questionnaire analysis AI-assisted audit preparation Compliance evidence review
• Module 19: AI Security Governance, Ethics & Privacy Responsible AI AI governance Data privacy Confidential security information Security-data handling AI access controls Shadow AI Third-party AI risks AI vendor assessment Human oversight Bias and reliabil
• Module 20: Integrated AI Cybersecurity Lab Participants work through a simulated security incident involving: Threat Intelligence → SIEM/Logs → AI Analysis → Alert Triage → Investigation → Incident Response → Threat Mapping → Risk Assessme
• Capstone Project AI-Powered Cybersecurity Investigation Participants receive a simulated organisational security incident and must: Identify the suspected attack. Analyse logs and threat intelligence. Use AI to assist investigation. Identify IoCs and TT
• Recommended Frameworks & Standards The course should explicitly reference: NIST Cybersecurity Framework 2.0 NIST Cyber AI Profile NIST AI Risk Management Framework OWASP GenAI/LLM Security MITRE ATLAS MITRE ATT&CK CIS Controls ISO/IEC 27001 concepts Inc

Application of AI in Cybersecurity

• Training manuals, practical exercises, and reference materials will be provided. Participants should come with a laptop and have basic knowledge of cybersecurity or IT. The training is practical and focuses on applying AI to real-world cybersecurity activities, including threat detection, incident response, threat intelligence, and AI security.