A Survey of Adversarial Examples in Computer Vision: Attack, Defense, and Beyond | Wuhan University Journal of Natural Sciences

Open Access

Review

Fig. 3

A schematic diagram of untargeted attacks (a) and targeted attacks (b) in the 2D feature space

$C_{i}$ denotes the label of the sample belonging to the $i$ -th class. In (a), $x$ of class $C_{1}$ is untargetedly attacked to satisfy $f_{θ} (x) = C_{i}$ where $i \neq 1$ ; In (b), $x$ of class $C_{1}$ is targetedly attacked to class $C_{2}$ to satisfy $f_{θ} (x) = C_{2}$

Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.

Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.

Initial download of the metrics may take a while.