Fair, privacy-preserving, and secure ML

Mikio Braun (Zalando)

2:05pm–2:45pm Wednesday, September 25, 2019

Location: 1A 12/14

Data Science, Machine Learning, & AI, Security and Privacy

Secondary topics: Ethics, Privacy and Security, Retail and e-commerce

Average rating:

(5.00, 1 rating)

Download slides (PDF)

Who is this presentation for?

Data scientists, managers, and product managers

Level

Intermediate

Description

As machine learning becomes mainstream, the side effects of using machine learning and AI on our lives have become increasingly visible. However, awareness for preserving privacy in ML models is rapidly growing. Companies have learned, often through painful experience, that you have to take extra measures to make machine learning models fair and unbiased. For example, we now know it’s possible that private data within training examples can be retrieved from a learned model without extra measures.

Mikio Braun explores techniques and concepts around fairness, privacy, and security when it comes to machine learning models.

Prerequisite knowledge

A working knowledge of how ML works and what typical ML-driven products are

What you'll learn

Learn limitations of ML and AI methods
Gain a better understanding of how ML methods make use of data
Get an overview of often-underrepresented topics like privacy and security when it comes to dealing with data-driven approaches

Mikio Braun

Zalando

Mikio Braun is a principal engineer for search at Zalando, one of Europe’s biggest fashion platforms. He worked in research for a number of years before becoming interested in putting research results to good use in the industry. Mikio holds a PhD in machine learning.