Attacking Machine Learning with Adversarial Examples

Adversarial examples are inputs to machine learning models that an attacker has intentionally designed to cause the model to make a mistake; they’re like optical illusions for machines. In this post we’ll show how adversarial examples work across differen… Read more

Read full article

Similar

On the Wrong Side of Algorithms – Discrimination and Biases in Machine Learning

We shape our tools and thereafter our tools shape us — Marshall McLuhan...

Notes on Causality in Machine Learning

I try to consolidate my MLSS 2020 notes in small blog posts and hope you might also find them interesting. I don’t try to cover the complete lectures but rather pick some pieces that I find important when working or doing research in ML. I anticipate this... (more…)

Algorithmic Aspects of Machine Learning

This course is organized around algorithmic issues that arise in machine learning. Modern machine learning systems are often built on top of algorithms that do not have provable guarantees, and it is the subject of debate when and why they work. In this c...

Build a Hamilton Song Recommendation SMS Bot with Machine Learning

What Hamilton song should you listen to right now? Recommend a song from the hit Broadway show and DisneyPlus movie using machine learning. (more…)

Introduction to Adversarial Machine Learning

Machine learning advancements lead to new ways to train models, as well as deceive them. This article discusses ways to train and defend against attacks. (more…)

Latest News

AI Heartache

EU threatens to force Meta to restore WhatsApp full access for rival AI chatbots

Lumen’s risky fiber bet nearly bankrupted it. Now it’s driving its AI future