Engineering Bias in Facial Recognition Workshop

From HOPE Wiki

Engineering Bias in Facial Recognition: Workshop and Safe Experimental Space workshop

Abstract

This workshop will demonstrate the facial recognition visualizer, which extracts live inferences from images of the face, including estimated age, gender, emotional expression, and more. The existing facial recognition visualizer software will be expanded with a prompt engineering component, in which the participant can develop a prompt that makes further assessments based on the appearance of an individual. During the workshops, participants will be invited to try out this software to experiment with different prompts. This workshop will reveal how readily AI and machine learning systems can be trained to make absolute determinations based on input data, even when those determinations are based on biased, incomplete assumptions. Given that any video-based surveillance system can be expanded to make these kinds of inferences, this workshop intends to give participants firsthand knowledge of how effortlessly biased determinations can be made based on facial surveillance data - and how risky these determinations actually are.

Day / Time / Location

Day 1, Friday, 15-August-2025, 3:30pm - 5:30pm
Tobin 219 (Workshop A)

Full Description

Registration -- NOT required

NOTE: You do NOT need to register to take this workshop
-- please show up early to ensure a seat at Tobin 219 (Workshop A).

Presenter(s)

Craig Fahner
Evan Light

Materials

Any materials needed to participate in this workshop will be available at-cost.
Observers are welcome at no cost.
To do the hands-on portion for this workshop:
Materials Cost: None

Required Software / What to bring

Links