From the course: MLOps Essentials: Model Deployment and Monitoring
Join today to access over 24,400 courses taught by industry experts.
Privacy in machine learning
From the course: MLOps Essentials: Model Deployment and Monitoring
Privacy in machine learning
- [Instructor] Similar to security, privacy is another important consideration in machine learning. Sensitive information should be protected against accidental or adversary leakage when used for training or inference. While security deals with protecting the entire data set or model, privacy focuses on protecting the sensitive parts while still providing access to the other parts for authorized users, like data scientists and analysts. Why do we need privacy protections? As the applications of AI are growing, so is the concern around its ability to infringe upon the rights and privacy of individuals. The first concern for building ML solutions is to gain customer and user trust. Users are worried about the misuse of their private data, and hence are unwilling to share this information for model training. There is concern around who gets to see their private data and if those individuals may steal and use it for unethical…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.
