A Validation Strategy for Deep Learning Models: Evaluating and Enhancing Robustness
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908555782651904 |
|---|---|
| author | Nuhu, Abdul-Rauf Kebria, Parham Hemmati, Vahid Lartey, Benjamin Mahmoud, Mahmoud Nabil Homaifar, Abdollah Tunstel, Edward |
| author_facet | Nuhu, Abdul-Rauf Kebria, Parham Hemmati, Vahid Lartey, Benjamin Mahmoud, Mahmoud Nabil Homaifar, Abdollah Tunstel, Edward |
| contents | Data-driven models, especially deep learning classifiers often demonstrate great success on clean datasets. Yet, they remain vulnerable to common data distortions such as adversarial and common corruption perturbations. These perturbations can significantly degrade performance, thereby challenging the overall reliability of the models. Traditional robustness validation typically relies on perturbed test datasets to assess and improve model performance. In our framework, however, we propose a validation approach that extracts "weak robust" samples directly from the training dataset via local robustness analysis. These samples, being the most susceptible to perturbations, serve as an early and sensitive indicator of the model's vulnerabilities. By evaluating models on these challenging training instances, we gain a more nuanced understanding of its robustness, which informs targeted performance enhancement. We demonstrate the effectiveness of our approach on models trained with CIFAR-10, CIFAR-100, and ImageNet, highlighting how robustness validation guided by weak robust samples can drive meaningful improvements in model reliability under adversarial and common corruption scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_19197 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Validation Strategy for Deep Learning Models: Evaluating and Enhancing Robustness Nuhu, Abdul-Rauf Kebria, Parham Hemmati, Vahid Lartey, Benjamin Mahmoud, Mahmoud Nabil Homaifar, Abdollah Tunstel, Edward Machine Learning Data-driven models, especially deep learning classifiers often demonstrate great success on clean datasets. Yet, they remain vulnerable to common data distortions such as adversarial and common corruption perturbations. These perturbations can significantly degrade performance, thereby challenging the overall reliability of the models. Traditional robustness validation typically relies on perturbed test datasets to assess and improve model performance. In our framework, however, we propose a validation approach that extracts "weak robust" samples directly from the training dataset via local robustness analysis. These samples, being the most susceptible to perturbations, serve as an early and sensitive indicator of the model's vulnerabilities. By evaluating models on these challenging training instances, we gain a more nuanced understanding of its robustness, which informs targeted performance enhancement. We demonstrate the effectiveness of our approach on models trained with CIFAR-10, CIFAR-100, and ImageNet, highlighting how robustness validation guided by weak robust samples can drive meaningful improvements in model reliability under adversarial and common corruption scenarios. |
| title | A Validation Strategy for Deep Learning Models: Evaluating and Enhancing Robustness |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2509.19197 |