Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.10298 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914033597153280 |
|---|---|
| author | Nayal, Laith Mousatat, Mahmoud Rasheed, Bader |
| author_facet | Nayal, Laith Mousatat, Mahmoud Rasheed, Bader |
| contents | Deep neural networks and Vision Transformers achieve state-of-the-art performance in computer vision but are highly vulnerable to adversarial perturbations. Standard defenses often incur high computational cost or lack formal guarantees. We propose a Lipschitz-guided stochastic depth (DropPath) method, where drop probabilities increase with depth to control the effective Lipschitz constant of the network. This approach regularizes deeper layers, improving robustness while preserving clean accuracy and reducing computation. Experiments on CIFAR-10 with ViT-Tiny show that our custom depth-dependent schedule maintains near-baseline clean accuracy, enhances robustness under FGSM, PGD-20, and AutoAttack, and significantly reduces FLOPs compared to baseline and linear DropPath schedules. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_10298 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Adversarial robustness through Lipschitz-Guided Stochastic Depth in Neural Networks Nayal, Laith Mousatat, Mahmoud Rasheed, Bader Computer Vision and Pattern Recognition Deep neural networks and Vision Transformers achieve state-of-the-art performance in computer vision but are highly vulnerable to adversarial perturbations. Standard defenses often incur high computational cost or lack formal guarantees. We propose a Lipschitz-guided stochastic depth (DropPath) method, where drop probabilities increase with depth to control the effective Lipschitz constant of the network. This approach regularizes deeper layers, improving robustness while preserving clean accuracy and reducing computation. Experiments on CIFAR-10 with ViT-Tiny show that our custom depth-dependent schedule maintains near-baseline clean accuracy, enhances robustness under FGSM, PGD-20, and AutoAttack, and significantly reduces FLOPs compared to baseline and linear DropPath schedules. |
| title | Adversarial robustness through Lipschitz-Guided Stochastic Depth in Neural Networks |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.10298 |