CapsAttacks: Robust and Imperceptible Adversarial Attacks on Capsule NetworksCapsAttacks: Robust and Imperceptible Adversarial Attacks on Capsule NetworksMarchisio, Alberto and Nanfa, Giorgio and Khalid, Faiq and Hanif, Muhammad Abdullah and Martina, Maurizio and Shafique, Muhammad2019
Paper summarydavidstutzMarchisio et al. propose a black-box adversarial attack on Capsule Networks. The main idea of the attack is to select pixels based on their local standard deviation. Given a window of allowed pixels to be manipulated, these are sorted based on standard deviation and possible impact on the predicted probability (i.e., gap between target class probability and maximum other class probability). A subset of these pixels is then manipulated by a fixed noise value $\delta$. In experiments, the attack is shown to be effective for CapsuleNetworks and other networks.
Also find this summary at [davidstutz.de](https://davidstutz.de/category/reading/).
Marchisio et al. propose a black-box adversarial attack on Capsule Networks. The main idea of the attack is to select pixels based on their local standard deviation. Given a window of allowed pixels to be manipulated, these are sorted based on standard deviation and possible impact on the predicted probability (i.e., gap between target class probability and maximum other class probability). A subset of these pixels is then manipulated by a fixed noise value $\delta$. In experiments, the attack is shown to be effective for CapsuleNetworks and other networks.
Also find this summary at [davidstutz.de](https://davidstutz.de/category/reading/).