New Research: Adversarial Machine Learning

A stop sign with pixelated stickers spelling love and hate

Last fall, a team of researchers with the Lab’s Ivan Evtimov, Earlence Fernandes, and Co-Director Yoshi Kohno shared research on ArXiv showing that malicious alterations to real world objects could cause devices to “misread” the image. Now, the team of researchers presented two papers updating this research – one at Computer Vision and Pattern Recognition (CVPR) 2018 and another at the 12th USENIX Workshop on Offensive Technologies (WOOT) 2018.