AI Security Engineering · Module 00

AI, ML & LLM Foundations Workbook

Learner: ______________________________   Date: ________________

A. Concept relationship map

Define each term in one sentence and draw their relationship.

TermCourse definitionSubset / contains / related toSecurity-relevant example
Artificial intelligence
Machine learning
Deep learning
Generative AI
Foundation model
Large language model

B. ML workflow

StageInputsOutputs / artifactQuality decisionSecurity concern
Collect / label
Split / transform
Train
Validate / tune
Test
Deploy / monitor

C. Neural-network trace

Input tensor: Forward-pass transformations: Output logits or values: Target: Loss: Gradient: Optimizer update: Parameter: Hyperparameters: Generalization check: Potential adversarial influence:

D. LLM request trace

StepInput / representationVersioned componentOutputTelemetry
Messages / template
Tokenization
Embeddings / Transformer
Logits / decoding
Output processing

E. Adaptation method selection

RequirementPromptRAGFine-tune / PEFTWhy
Current internal facts
Consistent response format
New domain behavior
Per-user private data

F. RAG trace

Source and owner: Parser and transformation: Chunking strategy: Metadata and ACL inheritance: Embedding model and version: Index / vector store: Query and identity: Authorization filter: Retrieval and reranking: Selected chunk lineage: Prompt augmentation: Generation: Citation validation: Metrics: Security boundaries:

G. Agent and MCP trace

ComponentIdentityData / authorityValidationAudit event
Host / application
MCP client
MCP server
Tool
Resource
Memory
Approval / execution

H. Metric selection

DecisionMetricDataset / trafficThresholdFailure costLimitation
Task quality
Retrieval
Security
Performance / cost

I. Terminology clinic

Rewrite this statement accurately using the course glossary:

“The AI learned our PDF during inference, stored it in its neural-network database, reasoned deterministically, and securely called the MCP API. The 95% accuracy score proves the agent is safe.”

J. Exit checklist

□ Concept map   □ ML lifecycle   □ LLM trace   □ RAG trace
□ Agent/MCP trace   □ Metrics   □ Terminology correction   □ Knowledge check