Adversarial Machine Learning Research on Display at Science Museum in London Through October 2020

Please note: The Museum reopened to the public on August 19th. Visitors must pre-book a free ticket in advance.

Please visit for further details.

Research exploring adversarial machine learning, or the ability to fool machine learning systems, is on display from June 2019 to October 2020 at the Science Museum in London as part of “Driverless: Who is in Control?” This free exhibit includes a modified stop sign developed by a team of researchers to fool driverless cars into misidentifying it and asks “can self-driving cars see the world as well as you can?”

This stop sign is part of research with the UW Tech Policy Lab along with Samsung Research North America, Stanford University, Stony Brook University, University of California at Berkeley, and University of Michigan that examines whether changes made to real world objects can trick machine learning systems into misidentifying them. Learn more about this research on our website and on the project website looking at road sign classifiers and object detectors.