Generative Adversarial Perturbations with Cross-paradigm Transferability on Localized Crowd Counting

ArXi:2603.24821v1 Announce Type: cross State-of-the-art crowd counting and localization are primarily modeled using two paradigms: density maps and point regression. Given the field's security ramifications, there is active interest in model robustness against adversarial attacks. Recent studies have nstrated transferability across density-map-based approaches via adversarial patches, but cross-paradigm attacks (i.e., across both density map-based models and point regression-based models) remain unexplored. We.