From the course: AI Product Security: Testing, Validation, and Maintenance
Unlock this course with a free trial
Join today to access over 25,300 courses taught by industry experts.
Setting up a testing lab
From the course: AI Product Security: Testing, Validation, and Maintenance
Setting up a testing lab
- [Narrator] When we're learning how to defend our AI systems, we need to have a test lab available to do our research and testing. For some systems, we'll use an online service such as ChatGPT. And we can also use an online lab, such as Google's Colab. However, there'll be some testing that we want to run locally. We may want to test pretrained models, we may want to augment the training of a pretrained model, or we may want to train our own models. If you haven't already installed them, you should install Python from the Microsoft Store onto your workstation, and then install Jupyter Notebooks using the command pip install jupyter. we can then start up Jupyter Notebooks with a command jupyter notebook. We're now in our local Notebook portal. We'll leave this for the moment and go check out CoLab. Google CoLab is a great resource for running testing, offering a free tier subscription which enables use not only of a…
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.
Contents
-
-
-
Introduction to AI security4m 38s
-
(Locked)
Security testing for AI applications3m 59s
-
(Locked)
Setting up a testing lab7m 10s
-
(Locked)
Introduction to HuggingFace5m 11s
-
(Locked)
Managing local models with ollama1m 49s
-
(Locked)
Test case management with KiwiTCMS1m 49s
-
(Locked)
Security testing with KiwiTCMS8m 33s
-
(Locked)
Understanding AI threats6m 26s
-
(Locked)
Testing requirements in AI standards2m 55s
-
-
-
-
-
-
-