A Mimetic Detector for Adversarial Image Perturbations

arXiv:2605.11492v1 Announce Type: new Abstract: Adversarial attacks fool deep image classifiers by adding tiny, almost invisible noise patterns to a clean image. The standard ell^infty-bounded attacks (FGSM, PGD, and the ell^infty variant of Carlini--Wagner) produce high-frequency, near-random sign patterns at the pixel level: nearly invisible in ell^2, but carrying disproportionate gradient energy. We exploit this with a single-shot, training-free detector using the high-order Corbino--Castillo mimetic operators from the open-source MOLE library. No retraining, no surrogate classifier, no access to the network under attack: the verdict is a property of the input alone, computed in O(HW) time. We validate the detector on the standard exttt{peppers} test image at the canonical ell^infty budget arepsilon = 16/255 and observe a clean-vs-adversarial separation that grows monotonically from 3.55imes at order k=2 to 4.19imes at k=6.

Source: arXiv cs.CV | 2026-05-13