In London? See our work on Adversarial Machine Learning at the Science Museum

In 2018, UW Security and Privacy Lab members Ivan Evtimov and Earlence Fernandes (now faculty at Wisconsin), along with UW Prof. Yoshi Kohno and researchers from Samsung Research North America, Stanford University, Stony Brook University, University of California at Berkeley, and University of Michigan , wrote a now widely sited paper on fooling computer vision classifiers and, in doing so, demonstrated the ability to fool a machine learning system into misidentifying a stop sign as, say, a speed limit sign.

The Science Museum in London asked to include the UW Stop Sign in their exhibit titled “Driverless: Who is in Control?”. If you’re in London, please stop by and check it out!