Representation of White- and Black-Box Adversarial Examples in Deep Neural Networks and Humans: A Functional Magnetic Resonance Imaging Study

no code implementations • 7 May 2019 • Chihye Han, Wonjun Yoon, Gihyun Kwon, Seungkyu Nam, Dae-shik Kim

However, DNNs exhibit idiosyncrasies that suggest their visual representation and processing might be substantially different from human vision.