Course Outline
Core Concepts in AI and Security
- Distinguishing the unique security characteristics of AI systems
- A holistic view of the AI lifecycle: data acquisition, training, inference, and deployment
- Classifying AI risks across technical, ethical, legal, and organizational dimensions
Distinct Threat Vectors in AI
- Adversarial examples and techniques for model manipulation
- Vulnerabilities related to model inversion and data exfiltration
- Data poisoning tactics during the training phase
- Specific risks in generative AI, such as LLM misuse and prompt injection
Frameworks for AI Security Risk Management
- The NIST AI Risk Management Framework (NIST AI RMF)
- ISO/IEC 42001 and other AI-dedicated standards
- Integrating AI risks into established enterprise GRC frameworks
Principles of AI Governance and Compliance
- Establishing AI accountability and audit trails
- Prioritizing transparency, explainability, and fairness as critical security attributes
- Managing bias, discrimination, and potential downstream negative impacts
Enterprise Preparedness and AI Security Policies
- Defining clear roles and responsibilities within AI security initiatives
- Developing policy components covering development, procurement, usage, and decommissioning
- Mitigating third-party risks and managing the use of supplier AI tools
Regulatory Environment and Global Developments
- An overview of the EU AI Act and broader international regulations
- The U.S. Executive Order concerning Safe, Secure, and Trustworthy AI
- Emerging national frameworks and industry-specific directives
Optional Workshop: Risk Mapping and Self-Evaluation
- Correlating real-world AI applications with NIST AI RMF functions
- Conducting a preliminary AI risk self-assessment
- Pinpointing internal deficiencies in AI security preparedness
Recap and Future Directions
Requirements
- A solid grasp of fundamental cybersecurity concepts
- Practical experience with IT governance or risk management frameworks
- General knowledge of AI concepts is advantageous but not mandatory
Target Audience
- IT security specialists
- Risk management professionals
- Compliance officers
Testimonials (3)
inventory and identifying the different risk exposures within AI
Gary Cook - Cybersecurity and Information Technology Risk Division
Course - Introduction to AI Trust, Risk, and Security Management (AI TRiSM)
I really enjoyed learning about AI attacks and the tools out there to begin practicing and actively using for security testing. I took a lot of knowledge away which I didn't have at the beginning and the course met what I hoped it would be. My favorite part shown from the training was Comet Browser and was amazed at what it could do. Definitely something will be looking into more. Overall it was a great course and enjoyed learning all OWASP GenAI Top 10.
Patrick Collins - Optum
Course - OWASP GenAI Security
The profesional knolage and the way how he presented it before us