Jiajun Lu, Hussein Sibai, Evan Fabry, David A. Forsyth. NO Need to Worry about Adversarial Examples in Object Detection in Autonomous Vehicles. CoRR abs/1707.03501, 2017.
Lu et al. present experiments regarding adversarial examples in the real world, i.e. after printing them. Personally, I find it interesting that researchers are studying how networks can be fooled by physically perturbing images. For me, one of the main conclusions it that it is very hard to evaluate the robustness of networks against physical perturbations. Often it is unclear whether changed lighting conditions, distances or viewpoints to objects might cause the network to fail – which means that the adversarial perturbation did not cause this failure.
Lu et al. present experiments regarding adversarial examples in the real world, i.e. after printing them. Personally, I find it interesting that researchers are studying how networks can be fooled by physically perturbing images. For me, one of the main conclusions it that it is very hard to evaluate the robustness of networks against physical perturbations. Often it is unclear whether changed lighting conditions, distances or viewpoints to objects might cause the network to fail – which means that the adversarial perturbation did not cause this failure.