Love Data: Data Poisoning with Glaze and Nightshade

Learn from Shawn Shan (Dartmouth College) about how Glaze and Nightshade can "poison" data to protect human art from AI scraping. 

Glaze is a system designed to protect human artists by disrupting style mimicry. At a high level, Glaze works by understanding the AI models that are training on human art, and using machine learning algorithms, computing a set of minimal changes to artworks, such that it appears unchanged to human eyes, but appears to AI models like a dramatically different art style.

Nightshade works similarly as Glaze, but instead of a defense against style mimicry, it is designed as an offense tool to distort feature representations inside generative AI image models.

This is a virtual event held on Zoom: https://rit.zoom.us/j/95955474603?

• February 10, 1PM [In-person]: AI, Data Centers, and Energy Use
• February 12, 1PM [Zoom]:Data Rescue Project
• February 18, 1PM [In-person]: Data Visualization: Painting with Weather Data in OpenProcessing
• February 26, 2PM [In-person]: Meme Epigraphy: Student-made Graffiti in RIT Campus Culture
• February 2 – 27: Data Scavenger Hunt

To request interpreting services, go to: http://myAccess.rit.edu/