Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2603.24821 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914422698541056 |
|---|---|
| author | Anisha, Alabi Mehzabin Wang, Guangjing Chellappan, Sriram |
| author_facet | Anisha, Alabi Mehzabin Wang, Guangjing Chellappan, Sriram |
| contents | 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 demonstrated 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 introduce a novel adversarial framework that compromises both density map and point regression architectural paradigms through a comprehensive multi-task loss optimization. For point-regression models, we employ scene-density-specific high-confidence logit suppression; for density-map approaches, we use peak-targeted density map suppression. Both are combined with model-agnostic perceptual constraints to ensure that perturbations are effective and imperceptible to the human eye. Extensive experiments demonstrate the effectiveness of our attack, achieving on average a 7X increase in Mean Absolute Error compared to clean images while maintaining competitive visual quality, and successfully transferring across seven state-of-the-art crowd models with transfer ratios ranging from 0.55 to 1.69. Our approach strikes a balance between attack effectiveness and imperceptibility compared to state-of-the-art transferable attack strategies. The source code is available at https://github.com/simurgh7/CrowdGen |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_24821 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Generative Adversarial Perturbations with Cross-paradigm Transferability on Localized Crowd Counting Anisha, Alabi Mehzabin Wang, Guangjing Chellappan, Sriram Computer Vision and Pattern Recognition Artificial Intelligence 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 demonstrated 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 introduce a novel adversarial framework that compromises both density map and point regression architectural paradigms through a comprehensive multi-task loss optimization. For point-regression models, we employ scene-density-specific high-confidence logit suppression; for density-map approaches, we use peak-targeted density map suppression. Both are combined with model-agnostic perceptual constraints to ensure that perturbations are effective and imperceptible to the human eye. Extensive experiments demonstrate the effectiveness of our attack, achieving on average a 7X increase in Mean Absolute Error compared to clean images while maintaining competitive visual quality, and successfully transferring across seven state-of-the-art crowd models with transfer ratios ranging from 0.55 to 1.69. Our approach strikes a balance between attack effectiveness and imperceptibility compared to state-of-the-art transferable attack strategies. The source code is available at https://github.com/simurgh7/CrowdGen |
| title | Generative Adversarial Perturbations with Cross-paradigm Transferability on Localized Crowd Counting |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2603.24821 |