The Four-Year Degree Isn't Dying — It's Evolving

Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

YouTube

The Hidden Dangers of Loading Open-Source AI Models

Yannic Kilcher via YouTube

Start learning Write review
Boot.dev Ad

Learn Backend Development Part-Time, Online

Learn More → Coursera Ad

Google AI Professional Certificate - Learn AI Skills That Get You Hired

Learn More →

Overview

AI, Data Science & Cloud Certificates from Google, IBM & Meta — 40% Off
One plan covers every Professional Certificate on Coursera. 40% off your first 3 months — limited time.
Unlock All Certificates
Explore the hidden dangers of loading open-source AI models in this eye-opening video. Discover how a seemingly innocent act of loading a model can potentially execute arbitrary code on your machine. Delve into the intricacies of Hugging Face model loading, the connection between PyTorch and pickle, and the inner workings of pickle data saving. Learn how to execute arbitrary code and examine the final code implementation. Gain valuable insights on protecting yourself from potential security risks associated with open-source AI models. This informative presentation covers essential topics for AI practitioners and enthusiasts, including model loading processes, data serialization, and cybersecurity best practices in the context of artificial intelligence.

Syllabus

- Introduction
- Sponsor: Weights & Biases
- How Hugging Face models are loaded
- From PyTorch to pickle
- Understanding how pickle saves data
- Executing arbitrary code
- The final code
- How can you protect yourself?

Taught by

Yannic Kilcher

Reviews

Start your review of The Hidden Dangers of Loading Open-Source AI Models

Start learning

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Sign up for free
Someone learning on their laptop while sitting on the floor.