Adversarial Perturbations of Physical Signals

arXiv:2402.17104v1 Announce Type: new
Abstract: We investigate the vulnerability of computer-vision-based signal classifiers to adversarial perturbations of their inputs, where the signals and perturbations are subject to physical constraints. We consider a scenario in which a source and interferer emit signals that propagate as waves to a detector, which attempts to classify the source by analyzing the spectrogram of the signal it receives using a pre-trained neural network. By solving PDE-constrained optimization problems, we construct interfering signals that cause the …

abstract adversarial arxiv classifiers computer constraints cs.cr cs.lg eess.sp inputs math.oc signal stat.ml type vision vulnerability