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

Generative Adversarial Perturbations with Cross-paradigm Transferability on Localized Crowd Counting explores A novel adversarial framework that compromises both density map and point regression crowd counting models with imperceptible perturbations, offering a new security layer for visual surveillance systems.. Commercial viability score: 7/10 in Adversarial Attacks.