Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2601.12624 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911384010227712 |
|---|---|
| author | Wang, Shiqi Khosravy, Mahdi Gupta, Neeraj Witkowski, Olaf |
| author_facet | Wang, Shiqi Khosravy, Mahdi Gupta, Neeraj Witkowski, Olaf |
| contents | Universal adversarial perturbations (UAPs) have garnered significant attention due to their ability to undermine deep neural networks across multiple inputs using a single noise pattern. Evolutionary algorithms offer a promising approach to generating such perturbations due to their ability to navigate non-convex, gradient-free landscapes. In this work, we introduce a float-coded, penalty-driven single-objective evolutionary framework for UAP generation that achieves lower visibility perturbations while enhancing attack success rates. Our approach leverages continuous gene representations aligned with contemporary deep learning scales, incorporates dynamic evolutionary operators with adaptive scheduling, and utilizes a modular PyTorch implementation for seamless integration with modern architectures. Additionally, we ensure the universality of the generated perturbations by testing across diverse models and by periodically switching batches to prevent overfitting. Experimental results on the ImageNet dataset demonstrate that our framework consistently produces perturbations with smaller norms, higher misclassification effectiveness, and faster convergence compared to existing evolutionary-based methods. These findings highlight the robustness and scalability of our approach for universal adversarial attacks across various deep learning architectures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_12624 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Towards Robust Universal Perturbation Attacks: A Float-Coded, Penalty-Driven Evolutionary Approach Wang, Shiqi Khosravy, Mahdi Gupta, Neeraj Witkowski, Olaf Machine Learning Computer Vision and Pattern Recognition Universal adversarial perturbations (UAPs) have garnered significant attention due to their ability to undermine deep neural networks across multiple inputs using a single noise pattern. Evolutionary algorithms offer a promising approach to generating such perturbations due to their ability to navigate non-convex, gradient-free landscapes. In this work, we introduce a float-coded, penalty-driven single-objective evolutionary framework for UAP generation that achieves lower visibility perturbations while enhancing attack success rates. Our approach leverages continuous gene representations aligned with contemporary deep learning scales, incorporates dynamic evolutionary operators with adaptive scheduling, and utilizes a modular PyTorch implementation for seamless integration with modern architectures. Additionally, we ensure the universality of the generated perturbations by testing across diverse models and by periodically switching batches to prevent overfitting. Experimental results on the ImageNet dataset demonstrate that our framework consistently produces perturbations with smaller norms, higher misclassification effectiveness, and faster convergence compared to existing evolutionary-based methods. These findings highlight the robustness and scalability of our approach for universal adversarial attacks across various deep learning architectures. |
| title | Towards Robust Universal Perturbation Attacks: A Float-Coded, Penalty-Driven Evolutionary Approach |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.12624 |