Fooling Computer Vision

Wiebe van Ranst joins us to talk about a project in which specially designed printed images can fool a computer vision system, preventing it from identifying a person. Their attack targets the popular YOLO2 pre-trained image recognition model, and thus, is likely to be widely applicable.

Guest

Wiebe van Ranst: Wiebe Van Ranst was born on the 9th of November 1990 in Bornem, Belgium. He got his bachelor's degree in Electronics-ICT (major ICT) in 2011. Two years after that in 2013 he got his master's degree on the same subject. Both Wiebe's bachelor's and master's thesis were about GPU processing which was still a very small field at the time. His bachelor's thesis was about setting up a benchmarking system for the GPU computation language OpenCL, and his master's thesis was about a 3D mesh simplification algorithm in the same OpenCL language. Starting a PhD was a logical continuation of this. Wiebe started his PhD in 2013, after finishing his master's thesis, under professor Joost Vennekens. His main interest then mainly focused on artificial intelligence in general and GPU computing. In 2016 Wiebe briefly worked on a start-up company called obtronics, focusing on computer vision, the technology of which was one year later taken over by the company RoboVision. During this experience Wiebe's interests shifted towards GPU processing for computer vision, and later also computer vision itself. His research was then also supervised by professor Toon Goedemé. Wiebe is currently active as a post-doctoral researcher in the EAVISE research group of KU Leuven. Currently, his research is on applying neural nets on embedded hardware.In his free time Wiebe is an active participant of ultra running and other endurance activities preferably in nature.