Course Outline
Overview of Threat Assessment for Artificial Intelligence Systems
- Vulnerability factors specific to AI architectures
- Comparison of AI attack surfaces against conventional systems
- Critical attack vectors across data, model, output, and interface layers
Adversarial Manipulation of AI Models
- Analyzing adversarial examples and perturbation methodologies
- Distinguishing between white-box and black-box attack scenarios
- Evaluation of FGSM, PGD, and DeepFool algorithms
- Techniques for visualizing and constructing adversarial samples
Model Inversion and Privacy Compromise
- Recovering training data from model outputs
- Assessing membership inference attack vectors
- Privacy implications in classification and generative model structures
Data Poisoning and Backdoor Implementations
- Mechanisms by which compromised data alters model performance
- Trigger-based backdoors and Trojan horse attack patterns
- Strategies for detection and data sanitization
Robustness Enhancement and Defensive Measures
- Implementation of adversarial training and data augmentation
- Application of gradient masking and input preprocessing controls
- Utilization of model smoothing and regularization techniques
Privacy-Preserving AI Security Controls
- Fundamental principles of differential privacy
- Managing noise injection and privacy budget allocation
- Adoption of federated learning and secure aggregation protocols
Operational AI Security Implementation
- Integrating threat awareness into model evaluation and deployment
- Applying the Adversarial Robustness Toolbox (ART) in practical settings
- Analysis of industry case studies regarding breaches and corrective actions
Conclusion and Recommended Progression
Requirements
- Proficiency in machine learning workflows and model training processes
- Practical experience with Python and standard ML frameworks, including PyTorch or TensorFlow
- Foundational knowledge of security or threat modeling concepts
Intended Audience
- Machine learning engineers
- Cybersecurity analysts
- AI researchers and model validation personnel
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
