Almost for Free: Crafting Adversarial Examples with Convolutional Image Filters

ArXi:2605.01098v1 Announce Type: new Adversarial examples in machine learning are typically generated using gradients, obtained either directly through access to the model or approximated via queries to it. In this paper, we propose a much simpler approach to craft adversarial examples, drawing inspiration from insights of explainable machine learning. In particular, we design \emph{adversarial image filters} that are based on classic edge detection algorithms but optimized to deceive learning models.