Model Online / On-Site
Duration
Modules 5 modules

Course Objective & Scope

Adding LLM features to enterprise software introduces far more than prompt injection alone: application security teams must also address XSS, SQLi and SSRF triggered by improper output handling, token/cost exhaustion (unbounded consumption), vector store weaknesses and insecure API integrations. This course covers the complete OWASP Top 10 for LLM Applications from a practical AppSec and secure coding perspective.

Participants work through attack-and-patch labs on a deliberately vulnerable LLM web application and leave with a reusable LLM security checklist and code review guide for their secure SDLC.

Who Should Attend?

  • Application security (AppSec) engineers and secure code review teams
  • Full-stack and backend developers integrating LLM APIs into products
  • Cybersecurity specialists and technical team leads
  • Prerequisite: familiarity with web/API security (OWASP Web/API Top 10) and basic Python or JavaScript

Key Takeaways

  • Map the OWASP Top 10 for LLM Applications onto existing web and API security controls
  • Identify direct and indirect prompt injection flaws and apply layered mitigations
  • Remediate second-order injection vulnerabilities where model outputs flow into HTML, SQL or internal APIs
  • Enforce rate, token and budget quotas against context-window exhaustion and Denial-of-Wallet attacks
  • Prepare an LLM security requirements checklist for enterprise SSDLC and peer code reviews

Curriculum

OWASP Top 10 for LLM Applications Through an AppSec Lens
  • Mapping the current OWASP LLM Top 10 risks onto application architecture components
  • Where classical OWASP Web/API Top 10 flaws intersect with LLM vulnerabilities
Direct and Indirect Prompt Injection: Attack and Defense
  • Instruction override, system prompt extraction and indirect injection through external content
  • Input classifiers, data/instruction separation, structured output schemas and least privilege
Improper Output Handling and Second-Order Injections
  • How LLM responses trigger browser XSS, server-side SSRF and database SQL injection
  • Output encoding, strict CSP policies, parameterised calls and zero-trust output validation
Unbounded Consumption (DoS / Denial of Wallet) and Side Channels
  • Max-token generation forcing, recursive agent loops and API cost exhaustion
  • Per-user/tenant token budgets, timeouts, semantic cache security and graceful fallback strategies
Attack-and-Patch Lab and SSDLC Security Checklist
  • Finding and fixing vulnerabilities in code on a deliberately vulnerable enterprise LLM web app
  • Building a reusable security checklist for pull-request reviews and release sign-off

Other Courses in This Category

  • AI Red Teaming and Machine Learning Model Penetration Testing

    Hands-on training on conducting end-to-end penetration tests against classical ML, deep learning and LLM APIs using MITRE ATLAS, Counterfit, ART, garak and PyRIT, and producing actionable pentest reports.

    Model Security & AI in Cybersecurity Corporate
    Live Course
    5 modules
    View
  • AI Applications in Cybersecurity Operations and Defense

    Hands-on training on applying machine learning and LLMs across cybersecurity—from phishing and malware detection to vulnerability prioritisation, cyber threat intelligence (CTI) analysis and SecOps assistants.

    Model Security & AI in Cybersecurity Corporate
    Live Course
    5 modules
    View
  • AI-Driven Cyber Threat Detection for Endpoint, Network and Cloud

    Teaches how to detect malware, ransomware, C2 traffic and multi-stage attack chains across EDR, NDR and cloud telemetry using behavioural machine learning, sequence models and graph analytics.

    Model Security & AI in Cybersecurity Corporate
    Live Course
    5 modules
    View
  • Anomaly Detection with Machine Learning for Security and Operations

    Teaches how to build unsupervised and semi-supervised anomaly detection pipelines on logs, network traffic and user behaviour (UEBA) using Isolation Forests, Autoencoders, time-series and graph methods while minimising false positives.

    Model Security & AI in Cybersecurity Corporate
    Live Course
    5 modules
    View
  • AI-Powered SIEM and Modern SOC Operations

    Teaches how to integrate LLM assistants, natural-language-to-KQL/SPL query generation, automated alert enrichment, triage agents and incident summarisation safely into SIEM, SOAR and modern SOC operations.

    Model Security & AI in Cybersecurity Corporate
    Live Course
    5 modules
    View
  • AI and Machine Learning Model Security Fundamentals

    Covers model extraction, membership inference, model inversion, poisoning and evasion attacks against machine learning and deep learning models using the MITRE ATLAS framework, along with practical defenses.

    Model Security & AI in Cybersecurity Corporate
    Live Course
    5 modules
    View

Get in touch