Hacking and Securing Machine Learning Systems and Environments

摘要

It is not an easy task to design and build machine learning systems. ML practitioners deploy ML models by converting some of their Jupyter Notebook Python code into production-ready application code. Once these ML systems have been set up, they need to be secured properly to manage vulnerabilities and exploits. There are different ways to attack ML systems and most data science teams are not equipped with the skills required to secure these systems. We will discuss in detail several strategies and solutions on how to secure these systems. In this session, we will review several attacks customized to take advantage of vulnerabilities present in Python libraries such as Joblib, urllib, and PyYAML. In addition to these, we'll check possible attacks on ML inference endpoints built using frameworks such as Flask, Pyramid, or Django. Finally, we will talk about several examples on how ML environments using ML frameworks (such as TensorFlow and PyTorch) can be attacked and compromised.

說明