Detailed content is being updated.
MAI-O02
AI Security and Red Teaming
Tấn công thử hệ AI của chính mình và dựng hàng rào bảo vệ
- Duration
- 16 hours
- Units
- 4 units
- Level
- Advanced
Overview
Course introduction
Tấn công thử hệ AI của chính mình và dựng hàng rào bảo vệ
What this course covers
- 1.Prompt Injection and Jailbreaks
- 2.Data Leakage via Tools and Memory
- 3.Input and Output Guardrails
- 4.Writing the Red Team Report
This course is for
Target audience
- Security engineer, AppSec, đội bảo mật
Entry requirements
Prerequisites
No prior knowledge is required.
Learning outcomes
After this course you will
- Có báo cáo red team kèm bộ guardrail đã triển khai
Course content
Public syllabus
Only approved public Unit and Topic outlines are shown.
Quality commitment
WHY CHOOSE MOCHI AI LEARNING
01
A unified Mochi AI platform
Programs, content, assessments and learning progress share one consistent experience.
02
Practice-led learning
Guided practice and checkpoints follow the approved structure of each published program.
03
Outcome-aligned pathways
Goals, prerequisites and learning outcomes make the expected capabilities explicit.
04
Governed outcome projects
Capstones and readiness criteria appear only after the program team publishes them.
05
Goal-based consultation
Discuss your needs and current foundation before choosing the right program.
Want to confirm this course is the right fit?
Discuss your goals, current foundation and implementation needs with our advisors.
Keep exploring
Related courses
Frequently Asked Questions

