Written by Kenny Song (@helloksong). Co-founder of Citadel AI. Fundamentally, a machine learning model is just a software program: it takes an input, steps through a series of computations, and produces an output. … [Read more...] about Breaking Your Neural Network with Adversarial Examples
Design
The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks (Research Summary)
Summary contributed by our researcher Erick Galinkin (@ErickGalinkin), who's also Principal AI Researcher at Rapid7. *Link to original paper + authors at the bottom. Overview: As neural networks, and … [Read more...] about The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks (Research Summary)
When Algorithms Infer Pregnancy or Other Sensitive Information About People
Written by Eric Siegel, PhD (@predictanalytic). He is the founder of Predictive Analytics World, and the instructor of the Coursera's Machine Learning for Everyone. *Originally published in Harvard Business … [Read more...] about When Algorithms Infer Pregnancy or Other Sensitive Information About People
Automating Informality: On AI and Labour in the Global South (Research Summary)
Summary contributed by Abhishek Gupta (@atg_abhishek), Founder and Principal Researcher of the Montreal AI Ethics Institute. His book Actionable AI Ethics will be published in 2021.This piece is part of a series of paper … [Read more...] about Automating Informality: On AI and Labour in the Global South (Research Summary)
Considerations for Closed Messaging Research in Democratic Contexts (Research summary)
Summary contributed by our learning community member Khoa Lam (Technology Strategy Researcher, Uncharted Power) *Link to original paper + authors at the bottom. Overview: Closed messaging apps such as … [Read more...] about Considerations for Closed Messaging Research in Democratic Contexts (Research summary)