Get in Touch

Course Outline

Introduction to AI Red Teaming

  • Understanding the AI threat landscape.
  • The role of red teams in AI security.
  • Ethical and legal considerations.

Adversarial Machine Learning

  • Types of attacks: evasion, poisoning, extraction, and inference.
  • Generating adversarial examples (e.g., FGSM, PGD).
  • Differentiating between targeted and untargeted attacks, along with success metrics.

Testing Model Robustness

  • Evaluating robustness under various perturbations.
  • Identifying model blind spots and failure modes.
  • Stress testing classification, vision, and NLP models.

Red Teaming AI Pipelines

  • Analyzing the attack surface of AI pipelines (data, model, and deployment layers).
  • Exploiting insecure model APIs and endpoints.
  • Reverse engineering model behavior and outputs.

Simulation and Tooling

  • Utilizing the Adversarial Robustness Toolbox (ART).
  • Conducting red teaming with tools such as TextAttack and IBM ART.
  • Employing sandboxing, monitoring, and observability tools.

AI Red Team Strategy and Defense Collaboration

  • Developing red team exercises and defining objectives.
  • Effectively communicating findings to blue teams.
  • Integrating red teaming activities into AI risk management frameworks.

Summary and Next Steps

Requirements

  • A solid understanding of machine learning and deep learning architectures.
  • Practical experience with Python and ML frameworks (such as TensorFlow or PyTorch).
  • Familiarity with cybersecurity principles or offensive security techniques.

Target Audience

  • Security researchers.
  • Offensive security teams.
  • Professionals involved in AI assurance and red teaming.
 14 Hours

Number of participants


Price per participant

Testimonials (2)

Upcoming Courses

Related Categories