OWASP GenAI Security Training Course

Day 1: Foundations and Core Threats

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

Learning Objectives:

• Comprehend the shift from standard OWASP Top 10 concerns to specific GenAI security challenges.
• Explore the ecosystem and resources available within the OWASP GenAI Security Project.
• Distinguish the fundamental differences between traditional application security and AI security.

Topics Covered:

• Overview of the mission and scope of the OWASP GenAI Security Project.
• Familiarization with the Threat Defense COMPASS framework.
• An analysis of the current AI security landscape and regulatory requirements.
• Comparing AI attack surfaces with traditional web application vulnerabilities.

Practical Exercise: Setup of the OWASP Threat Defense COMPASS tool and execution of an initial threat assessment.

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

Learning Objectives:

• Gain mastery over the first five critical LLM vulnerabilities.
• Understand various attack vectors and exploitation techniques.
• Apply practical mitigation strategies to address these risks.

Topics Covered:

LLM01: Prompt Injection

• Techniques for direct and indirect prompt injection.
• Hidden instruction attacks and cross-prompt contamination.
• Practical examples: Jailbreaking chatbots and bypassing safety measures.
• Defense strategies: Input sanitization, prompt filtering, and differential privacy.

LLM02: Sensitive Information Disclosure

• Extraction of training data and leakage of system prompts.
• Analysis of model behavior to identify sensitive information exposure.
• Considerations regarding privacy implications and regulatory compliance.
• Mitigation measures: Output filtering, access controls, and data anonymization.

LLM03: Supply Chain Vulnerabilities

• Security concerns related to third-party model dependencies and plugins.
• Compromised training datasets and model poisoning risks.
• Vendor risk assessment specifically for AI components.
• Best practices for secure model deployment and verification.

Practical Exercise: A hands-on lab demonstrating prompt injection attacks against vulnerable LLM applications and implementing corresponding 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: Data validation pipelines and provenance tracking.

LLM05: Improper Output Handling

• Securing the processing of LLM-generated content.
• Preventing code injection through AI-generated outputs.
• Mitigating cross-site scripting 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.
• Management of agent authority and permissions.
• Addressing unintended system interactions and privilege escalation.
• Implementation of guardrails and human oversight controls.

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 that include appropriate access controls and monitoring.

Day 2: Advanced Threats and Implementation

Module 5: Emerging AI Threats (2 hours)

Learning Objectives:

• Understand cutting-edge AI security threats.
• Implement advanced detection and prevention techniques.
• Design AI systems that are resilient against sophisticated attacks.

Topics Covered:

LLM08: Vector and Embedding Weaknesses

• Vulnerabilities in RAG systems and vector database security.
• Attacks involving embedding poisoning and similarity manipulation.
• Handling adversarial examples in semantic search.
• Securing vector stores and implementing anomaly detection.

LLM09: Misinformation and Model Reliability

• Detection and mitigation of hallucinations.
• Considerations for bias amplification and fairness.
• Mechanisms for fact-checking and source verification.
• Integration of content validation and human oversight.

LLM10: Unbounded Consumption

• Resource exhaustion and denial-of-service attacks.
• Strategies for rate limiting and resource management.
• Cost optimization and budget controls.
• Performance monitoring and alerting systems.

Practical Exercise: Building a secure RAG pipeline that includes vector database protection and hallucination detection.

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 suitable for multi-agent environments.

Topics Covered:

• Introduction to Agentic AI and autonomous systems.
• 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: 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 assessment into organizational security programs.
• Develop comprehensive strategies for AI risk management.

Topics Covered:

• In-depth analysis of the Threat Defense COMPASS methodology.
• Integration of the OODA Loop: Observe, Orient, Decide, Act.
• Mapping threats to the MITRE ATT&CK and ATLAS frameworks.
• Construction of AI Threat Resilience Strategy Dashboards.
• Integration with existing security tools and processes.

Practical Exercise: Performing a complete 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 ground up.
• Implement monitoring and incident response 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.
• Deployment security and production hardening.

Monitoring and Detection:

• Specific logging and monitoring requirements for AI.
• Anomaly detection techniques for AI systems.
• Incident response procedures for AI security events.
• Forensics and investigation techniques.

Governance and Compliance:

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

Practical Exercise: Designing a complete 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 detection and prevention capabilities.

Topics Covered:

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

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: Deepfakes, advanced prompt injection, and model inversion.
• Future developments and the roadmap for the OWASP GenAI project.
• Building AI security communities and fostering knowledge sharing.
• Continuous improvement and the integration of threat intelligence.

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