One lesson
An individual lesson
This track has no lesson ready to buy yet. Each lesson becomes available only after it is built and reviewed.
$5.00Not available yet
All course tracks
AI and machine learning · 30 lessons · up to 10 minutes each
AI Safety, Privacy, and Security
A planned safety path for protecting data, limiting tools, and checking unsafe inputs.
Coming Soon
One-time purchase · USD
Choose what to unlock
Access is attached to your account after payment is verified. No subscription.
Full category
AI Safety, Privacy, and Security
Permanent access to the lessons published in this track when you buy. Future lessons are not included. 0 of 30 lessons are published; 0 are in owner review and 30 are Coming Soon.
$29.0030 lessons still in progress
Beginner
Lessons 1–10
01 AI Safety, Privacy, and Security: Sketch data classification
Topic: data classification
Draw a small map of data classification in the context of AI trust boundaries, privacy controls, and misuse testing; save a short example or check that demonstrates the result.
Beginner4 minComing Soon02 AI Safety, Privacy, and Security: Name the parts of prompt injection surfaces
Topic: prompt injection surfaces
Label the main pieces in prompt injection surfaces in the context of AI trust boundaries, privacy controls, and misuse testing; save a short example or check that demonstrates the result.
Beginner5 minComing Soon03 AI Safety, Privacy, and Security: Trace an example of untrusted input boundaries
Topic: untrusted input boundaries
Follow one input through untrusted input boundaries in the context of AI trust boundaries, privacy controls, and misuse testing; save a short example or check that demonstrates the result.
Beginner6 minComing Soon04 AI Safety, Privacy, and Security: Compare choices for least-privilege tools
Topic: least-privilege tools
Write down one practical difference between least-privilege tools in the context of AI trust boundaries, privacy controls, and misuse testing; save a short example or check that demonstrates the result.
Beginner7 minComing Soon05 AI Safety, Privacy, and Security: Find the boundary in private data handling
Topic: private data handling
Mark where private data handling in the context of AI trust boundaries, privacy controls, and misuse testing; save a short example or check that demonstrates the result.
Beginner8 minComing Soon06 AI Safety, Privacy, and Security: Inspect an example of harm and refusal cases
Topic: harm and refusal cases
Annotate a minimal example of harm and refusal cases in the context of AI trust boundaries, privacy controls, and misuse testing; save a short example or check that demonstrates the result.
Beginner9 minComing Soon07 AI Safety, Privacy, and Security: Connect output validation to a neighboring concept
Topic: output validation
Show how output validation in the context of AI trust boundaries, privacy controls, and misuse testing; save a short example or check that demonstrates the result.
Beginner10 minComing Soon08 AI Safety, Privacy, and Security: Spot a failure mode in retention and deletion
Topic: retention and deletion
Describe one likely failure for retention and deletion in the context of AI trust boundaries, privacy controls, and misuse testing; save a short example or check that demonstrates the result.
Beginner3 minComing Soon09 AI Safety, Privacy, and Security: Read an official example of red-team test cases
Topic: red-team test cases
Summarize an official example of red-team test cases in the context of AI trust boundaries, privacy controls, and misuse testing; save a short example or check that demonstrates the result.
Beginner5 minComing Soon10 AI Safety, Privacy, and Security: Choose a use case for incident and audit trail
Topic: incident and audit trail
Match one small use case to incident and audit trail in the context of AI trust boundaries, privacy controls, and misuse testing; save a short example or check that demonstrates the result.
Beginner6 minComing Soon
Intermediate
Lessons 11–20
11 AI Safety, Privacy, and Security: Build an example with data classification
Topic: data classification
Create a small working example that uses data classification in the context of AI trust boundaries, privacy controls, and misuse testing; save a short example or check that demonstrates the result.
Intermediate4 minComing Soon12 AI Safety, Privacy, and Security: Compose prompt injection surfaces with another component
Topic: prompt injection surfaces
Combine prompt injection surfaces in the context of AI trust boundaries, privacy controls, and misuse testing; save a short example or check that demonstrates the result.
Intermediate5 minComing Soon13 AI Safety, Privacy, and Security: Configure untrusted input boundaries for a small case
Topic: untrusted input boundaries
Set up untrusted input boundaries in the context of AI trust boundaries, privacy controls, and misuse testing; save a short example or check that demonstrates the result.
Intermediate6 minComing Soon14 AI Safety, Privacy, and Security: Validate inputs around least-privilege tools
Topic: least-privilege tools
Add a check around least-privilege tools in the context of AI trust boundaries, privacy controls, and misuse testing; save a short example or check that demonstrates the result.
Intermediate7 minComing Soon15 AI Safety, Privacy, and Security: Use private data handling in a short workflow
Topic: private data handling
Add private data handling in the context of AI trust boundaries, privacy controls, and misuse testing; save a short example or check that demonstrates the result.
Intermediate8 minComing Soon16 AI Safety, Privacy, and Security: Refactor harm and refusal cases into a reusable unit
Topic: harm and refusal cases
Extract harm and refusal cases in the context of AI trust boundaries, privacy controls, and misuse testing; save a short example or check that demonstrates the result.
Intermediate9 minComing Soon17 AI Safety, Privacy, and Security: Exercise output validation with sample data
Topic: output validation
Run sample data through output validation in the context of AI trust boundaries, privacy controls, and misuse testing; save a short example or check that demonstrates the result.
Intermediate10 minComing Soon18 AI Safety, Privacy, and Security: Observe retention and deletion outputs
Topic: retention and deletion
Capture the result of retention and deletion in the context of AI trust boundaries, privacy controls, and misuse testing; save a short example or check that demonstrates the result.
Intermediate3 minComing Soon19 AI Safety, Privacy, and Security: Recover from a red-team test cases failure
Topic: red-team test cases
Handle one expected failure from red-team test cases in the context of AI trust boundaries, privacy controls, and misuse testing; save a short example or check that demonstrates the result.
Intermediate5 minComing Soon20 AI Safety, Privacy, and Security: Document incident and audit trail behavior
Topic: incident and audit trail
Write a short usage note for incident and audit trail in the context of AI trust boundaries, privacy controls, and misuse testing; save a short example or check that demonstrates the result.
Intermediate6 minComing Soon
Advanced
Lessons 21–30
21 AI Safety, Privacy, and Security: Test a boundary around data classification
Topic: data classification
Add an edge-case test for data classification in the context of AI trust boundaries, privacy controls, and misuse testing; save a short example or check that demonstrates the result.
Advanced4 minComing Soon22 AI Safety, Privacy, and Security: Harden prompt injection surfaces
Topic: prompt injection surfaces
Add the relevant access, safety, or validation control to prompt injection surfaces in the context of AI trust boundaries, privacy controls, and misuse testing; save a short example or check that demonstrates the result.
Advanced5 minComing Soon23 AI Safety, Privacy, and Security: Measure untrusted input boundaries
Topic: untrusted input boundaries
Record a small baseline for untrusted input boundaries in the context of AI trust boundaries, privacy controls, and misuse testing; save a short example or check that demonstrates the result.
Advanced6 minComing Soon24 AI Safety, Privacy, and Security: Reduce cost in least-privilege tools
Topic: least-privilege tools
Change one measurable cost in least-privilege tools in the context of AI trust boundaries, privacy controls, and misuse testing; save a short example or check that demonstrates the result.
Advanced7 minComing Soon25 AI Safety, Privacy, and Security: Diagnose a private data handling failure
Topic: private data handling
Use an observable signal to explain a failure in private data handling in the context of AI trust boundaries, privacy controls, and misuse testing; save a short example or check that demonstrates the result.
Advanced8 minComing Soon26 AI Safety, Privacy, and Security: Make harm and refusal cases repeatable
Topic: harm and refusal cases
Show that rerunning harm and refusal cases in the context of AI trust boundaries, privacy controls, and misuse testing; save a short example or check that demonstrates the result.
Advanced9 minComing Soon27 AI Safety, Privacy, and Security: Review trade-offs in output validation
Topic: output validation
Compare two documented approaches to output validation in the context of AI trust boundaries, privacy controls, and misuse testing; save a short example or check that demonstrates the result.
Advanced10 minComing Soon28 AI Safety, Privacy, and Security: Improve retention and deletion maintainability
Topic: retention and deletion
Refine retention and deletion in the context of AI trust boundaries, privacy controls, and misuse testing; save a short example or check that demonstrates the result.
Advanced3 minComing Soon29 AI Safety, Privacy, and Security: Verify red-team test cases end to end
Topic: red-team test cases
Check that a complete small flow using red-team test cases in the context of AI trust boundaries, privacy controls, and misuse testing; save a short example or check that demonstrates the result.
Advanced5 minComing Soon30 AI Safety, Privacy, and Security: Audit incident and audit trail against its source docs
Topic: incident and audit trail
Check the implementation of incident and audit trail in the context of AI trust boundaries, privacy controls, and misuse testing; save a short example or check that demonstrates the result.
Advanced6 minComing Soon
Reference documentation
References support the selected track topics while its lesson content is built and reviewed progressively.
This track is a catalog outline only. Each lesson remains unavailable until it is built and personally reviewed.