Privacy-Preserving Machine Learning
A use-case-driven approach to building and protecting ML pipelines from privacy and security threats
Created by Srinivasa Rao Aravilli
Explore practical ways to protect sensitive data while building and deploying machine learning models. Learn how to address privacy threats, implement privacy-preserving techniques, and navigate real-world security challenges in ML pipelines. Gain the skills needed to keep your data secure and compliant.
Packt | May 2024 | 402 min
What You Will Learn
You will start by understanding the main privacy threats in machine learning and why data protection is essential. Through step-by-step explanations and hands-on examples, you will learn to apply techniques like federated learning and differential privacy. Real-world use cases and practical exercises help you put these concepts into action.
Key Features
- Identify and mitigate privacy risks in machine learning workflows
- Build privacy-preserving ML pipelines using open-source frameworks
- Apply confidential computing to defend against memory-based data attacks
Target Audience
Ideal for data scientists, machine learning engineers, and privacy engineers with a solid grasp of mathematics and experience using frameworks like TensorFlow, PyTorch, or scikit-learn. If you want to strengthen your ability to secure ML pipelines and protect sensitive information, you will find practical guidance and actionable skills here.
