A Validation Strategy for Deep Learning Models: Evaluating and Enhancing Robustness

Abdul-Rauf Nuhu

doi:10.1109/OJCS.2025.3650722

A Validation Strategy for Deep Learning Models: Evaluating and Enhancing Robustness

2026-01-01

0

PRE

AI

DOI：10.1109/OJCS.2025.3650722

Original

Original request for help

Save

Abstract

En 中文

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.

Keywords:

Adversarial robustness

common corruption robustness

deep learning models

model validation

weak robust samples

Adversarial robustness

common corruption robustness

deep learning models

model validation

weak robust samples

A Validation Strategy for Deep Learning Models: Evaluating and Enhancing Robustness

Abstract

Journal

Organization