Blar i NTNU Open på forfatter "Midtlid, Kim André"
-
Magnitude Adversarial Spectrum Search-based Black-box Attack against Image Classification
Midtlid, Kim André; Åsheim, Johannes; Li, Jingyue (Chapter, 2022)Recent development has revealed that deep neural networks used in image classification systems are vulnerable to adversarial attacks. Thus, it is critical to understand the possible adversarial attacks to develop effective ... -
Understanding Black-Box Attacks Against Object Detectors from a User's Perspective
Midtlid, Kim André; Åsheim, Johannes; Li, Jingyue (Chapter, 2022)Due to recent developments in object detection systems, and the realistic threat of black-box adversarial attacks on object detector models, we argue the need for a contextual understanding of the attacks from the users’ ...