Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Course Outline
The AI Threat Landscape
- Understanding why AI security is distinct: non-determinism, opaque reasoning, and prompts as an attack surface.
- Attack taxonomy: attacks during training, inference, and the supply chain.
- The ML adversary model: understanding who targets AI systems and their motivations.
OWASP Top 10 for LLM Applications
- Prompt injection: direct and indirect attack vectors.
- Insecure output handling and cross-plugin request forgery.
- Training data poisoning and supply chain vulnerabilities.
- Model denial of service, sensitive information disclosure, and excessive agency.
- Hands-on lab: exploiting each OWASP category against a test application.
Prompt Injection and Jailbreak Red Teaming
- Taxonomy of injection techniques: direct, indirect, multi-turn, and multi-modal.
- Automated red-teaming using Giskard, Garak, and custom fuzzing tools.
- Jailbreak classification and defense evaluation.
- Building a red-team harness for continuous LLM security testing.
Model-Level Attacks and Defenses
- Model extraction: stealing model weights and functionality via API queries.
- Membership inference: determining if specific data was part of the training set.
- Adversarial examples: perturbations designed to fool classifiers and embeddings.
- Data poisoning: corrupting training data to introduce backdoors or degrade performance.
Input and Output Security Controls
- Input sanitization methods that go beyond traditional web defenses.
- Output filtering: addressing toxicity, PII leakage, and hallucinated code execution.
- Guardrails as security infrastructure: leveraging NeMo, Guardrails AI, and custom policies.
- Structured output enforcement as a security boundary.
AI Supply Chain Security
- Model provenance: verifying the authenticity and integrity of models.
- Dependency scanning for ML frameworks and model formats.
- Secure model serving: sandboxing, network isolation, and least-privilege access.
- Vetting fine-tuned and community models for embedded malware.
Operational Security for AI Systems
- Access control for model endpoints, vector stores, and agent tools.
- Audit logging for every model interaction and decision made.
- Incident response strategies for AI-specific breaches, including scenarios where the model itself is compromised.
- Continuous security testing integrated into CI/CD for ML pipelines.
Building an AI Security Program
- AI security maturity models and roadmaps.
- Integrating AI security into existing Application Security (AppSec) and cloud security programs.
- Governance frameworks and emerging regulations for AI systems.
- Creating and maintaining an organizational AI security playbook.
Requirements
- Experience in deploying ML models or LLM applications in production environments.
- Familiarity with security concepts, including authentication, authorization, and threat modeling.
- Proficiency in Python for conducting adversarial testing exercises.
Target Audience
- Security engineers looking to expand their expertise into AI/ML threat surfaces.
- ML engineers responsible for ensuring model safety and robustness.
- Red team members incorporating AI systems into their testing scope.
14 Hours
