OWASP GenAI Security Training Course

Day 1: Foundations and Core Threats

Module 1: Introduction to the OWASP GenAI Security Project (1 hour)

Learning Objectives:

• Understand the progression from the OWASP Top 10 to security challenges specific to GenAI.
• Explore the ecosystem and resources of the OWASP GenAI Security Project.
• Distinguish between traditional application security and AI-specific security requirements.

Topics Covered:

• Overview of the mission and scope of the OWASP GenAI Security Project.
• Introduction to the Threat Defense COMPASS framework.
• Understanding the AI security landscape and associated regulatory requirements.
• Comparing AI attack surfaces with traditional web application vulnerabilities.

Practical Exercise: Setting up the OWASP Threat Defense COMPASS tool and conducting an initial threat assessment.

Module 2: OWASP Top 10 for LLMs - Part 1 (2.5 hours)

Learning Objectives:

• Gain proficiency in the first five critical LLM vulnerabilities.
• Understand relevant attack vectors and exploitation techniques.
• Apply practical strategies for mitigation.

Topics Covered:

LLM01: Prompt Injection

• Techniques for direct and indirect prompt injection.
• Hidden instruction attacks and cross-prompt contamination.
• Practical examples, including jailbreaking chatbots and bypassing safety measures.
• Defense strategies such as input sanitization, prompt filtering, and differential privacy.

LLM02: Sensitive Information Disclosure

• Extraction of training data and leakage of system prompts.
• Analyzing model behavior for potential sensitive information exposure.
• Considerations for privacy implications and regulatory compliance.
• Mitigation techniques including output filtering, access controls, and data anonymization.

LLM03: Supply Chain Vulnerabilities

• Security of third-party model dependencies and plugins.
• Risks related to compromised training datasets and model poisoning.
• Conducting vendor risk assessments for AI components.
• Best practices for secure model deployment and verification.

Practical Exercise: A hands-on lab demonstrating prompt injection attacks on vulnerable LLM applications and implementing defensive measures.

Module 3: OWASP Top 10 for LLMs - Part 2 (2 hours)

Topics Covered:

LLM04: Data and Model Poisoning

• Techniques for manipulating training data.
• Modifying model behavior through poisoned inputs.
• Backdoor attacks and methods for data integrity verification.
• Prevention strategies such as data validation pipelines and provenance tracking.

LLM05: Improper Output Handling

• Insecure processing of content generated by LLMs.
• Code injection risks arising from AI-generated outputs.
• Cross-site scripting vulnerabilities via AI responses.
• Frameworks for output validation and sanitization.

Practical Exercise: Simulating data poisoning attacks and implementing robust output validation mechanisms.

Module 4: Advanced LLM Threats (1.5 hours)

Topics Covered:

LLM06: Excessive Agency

• Risks associated with autonomous decision-making and boundary violations.
• Managing agent authority and permissions.
• Unintended system interactions and potential privilege escalation.
• Implementing guardrails and controls for human oversight.

LLM07: System Prompt Leakage

• Vulnerabilities related to the exposure of system instructions.
• Disclosure of credentials and logic through prompts.
• Techniques used by attackers to extract system prompts.
• Securing system instructions and external configurations.

Practical Exercise: Designing secure agent architectures with appropriate access controls and monitoring capabilities.

Day 2: Advanced Threats and Implementation

Module 5: Emerging AI Threats (2 hours)

Learning Objectives:

• Understand cutting-edge security threats in the AI domain.
• Implement advanced techniques for detection and prevention.
• Design resilient AI systems capable of withstanding sophisticated attacks.

Topics Covered:

LLM08: Vector and Embedding Weaknesses

• Vulnerabilities in RAG systems and vector database security.
• Embedding poisoning and attacks involving similarity manipulation.
• Adversarial examples in semantic search contexts.
• Securing vector stores and implementing anomaly detection.

LLM09: Misinformation and Model Reliability

• Methods for detecting and mitigating hallucinations.
• Addressing bias amplification and fairness considerations.
• Mechanisms for fact-checking and source verification.
• Integrating content validation and human oversight.

LLM10: Unbounded Consumption

• Resource exhaustion and denial-of-service attack vectors.
• Strategies for rate limiting and resource management.
• Cost optimization and budget control measures.
• Systems for performance monitoring and alerting.

Practical Exercise: Building a secure RAG pipeline with vector database protection and hallucination detection capabilities.

Module 6: Agentic AI Security (2 hours)

Learning Objectives:

• Understand the unique security challenges posed by autonomous AI agents.
• Apply the OWASP Agentic AI taxonomy to real-world systems.
• Implement security controls for multi-agent environments.

Topics Covered:

• Introduction to Agentic AI and autonomous systems.
• The OWASP Agentic AI Threat Taxonomy, covering Agent Design, Memory, Planning, Tool Use, and Deployment.
• Security and coordination risks in multi-agent systems.
• Attacks involving tool misuse, memory poisoning, and goal hijacking.
• Securing agent communication and decision-making processes.

Practical Exercise: Conducting a threat modeling exercise using the OWASP Agentic AI taxonomy on a multi-agent customer service system.

Module 7: OWASP Threat Defense COMPASS Implementation (2 hours)

Learning Objectives:

• Master the practical application of Threat Defense COMPASS.
• Integrate AI threat assessments into organizational security programs.
• Develop comprehensive strategies for AI risk management.

Topics Covered:

• A deep dive into the Threat Defense COMPASS methodology.
• Integrating the OODA Loop: Observe, Orient, Decide, Act.
• Mapping threats to the MITRE ATT&CK and ATLAS frameworks.
• Constructing dashboards for AI Threat Resilience Strategies.
• Integrating with existing security tools and processes.

Practical Exercise: Completing a threat assessment using COMPASS for a Microsoft Copilot deployment scenario.

Module 8: Practical Implementation and Best Practices (2.5 hours)

Learning Objectives:

• Design secure AI architectures from the foundational level.
• Implement monitoring and incident response mechanisms for AI systems.
• Create governance frameworks for AI security.

Topics Covered:

Secure AI Development Lifecycle:

• Security-by-design principles for AI applications.
• Code review practices for LLM integrations.
• Testing methodologies and vulnerability scanning techniques.
• Deployment security and production hardening strategies.

Monitoring and Detection:

• Logging and monitoring requirements specific to AI.
• Anomaly detection tailored for AI systems.
• Incident response procedures for AI security events.
• Forensic and investigation techniques.

Governance and Compliance:

• Frameworks and policies for AI risk management.
• Regulatory compliance considerations, including GDPR and the AI Act.
• Third-party risk assessments for AI vendors.
• Security awareness training for AI development teams.

Practical Exercise: Designing a comprehensive security architecture for an enterprise AI chatbot, including monitoring, governance, and incident response procedures.

Module 9: Tools and Technologies (1 hour)

Learning Objectives:

• Evaluate and implement AI security tools.
• Understand the current landscape of AI security solutions.
• Build practical capabilities for detection and prevention.

Topics Covered:

• The ecosystem and vendor landscape for AI security tools.
• Open-source security tools, including Garak, PyRIT, and Giskard.
• Commercial solutions for AI security and monitoring.
• Integration patterns and deployment strategies.
• Criteria and frameworks for tool selection and evaluation.

Practical Exercise: A hands-on demonstration of AI security testing tools and planning for their implementation.

Module 10: Future Trends and Wrap-up (1 hour)

Learning Objectives:

• Understand emerging threats and future security challenges.
• Develop strategies for continuous learning and improvement.
• Create action plans for organizational AI security programs.

Topics Covered:

• Emerging threats such as deepfakes, advanced prompt injection, and model inversion.
• Future developments and the roadmap for OWASP GenAI projects.
• Building AI security communities and facilitating knowledge sharing.
• Integrating continuous improvement and threat intelligence.

Action Planning Exercise: Developing a 90-day action plan for implementing OWASP GenAI security practices within participants' organizations.