Owned By Statistics - How Kubeflow & MLOps Can Help Secure Your ML Workloads
Offered By: CNCF [Cloud Native Computing Foundation] via YouTube
Course Description
Overview
Syllabus
Introduction
Machine Learning at Microsoft
ML in every product at Microsoft
ML in the average enterprise
Data scientist
Building a model
Rolling it out
Security
Three types of attacks
Advanced models
Snow detection
Stop sign detection
Face recognition
Defend against adversaries
Build an MLOps pipeline
Modular components
Pipeline example
Another attack vector
Malicious users
Two types of attacks
Distillation attack
Accuracy
GoogleBERT
Continuous Improvement
Build Efficient Pipelines
Take Your Models
Hidden Data
Recommendations
Network Graph
Map Leakage
Example
How to prevent this
Injections
Leaks
Summary
The Reality
You will be attacked
Conclusion
Questions
Reprocessing ML Pipeline Predictions
MLOps vs Continuous Machine Learning
Regulation of ML
Mitigating Leaky Data
Taught by
CNCF [Cloud Native Computing Foundation]
Related Courses
Building Geospatial Apps on Postgres, PostGIS, & Citus at Large ScaleMicrosoft via YouTube Unlocking the Power of ML for Your JavaScript Applications with TensorFlow.js
TensorFlow via YouTube Managing the Reactive World with RxJava - Jake Wharton
ChariotSolutions via YouTube What's New in Grails 2.0
ChariotSolutions via YouTube Performance Analysis of Apache Spark and Presto in Cloud Environments
Databricks via YouTube