Systematic Evaluation of Robustness in Fine-tuned Models

Angela John, Hamayoon BehmanusharXiv 2026 · arXiv

TL;DR

This paper systematically evaluates how fine-tuning popular pre-trained models—ResNet50, DenseNet121, and MobileNet-V2—impacts their robustness against adversarial attacks. The researchers demonstrate that a model's resilience is highly dependent on the specific combination of architecture, dataset distribution, and attack type, providing a roadmap for selecting models that balance performance with security.

What Problem Does This Paper Address?

In modern deep learning, we rarely train from scratch. Instead, we use "pre-trained" models—networks already trained on massive datasets like ImageNet—and "fine-tune" them for specific tasks. While this saves immense computational time and money, it introduces a security blind spot: Robustness.

We know these models perform well on clean data, but how do they behave when faced with "adversarial examples" (images subtly altered to fool a computer)? Does fine-tuning a model on a small dataset like MNIST make it more or less vulnerable than fine-tuning it on a complex one like CIFAR100? This paper fills the gap by providing a comparative analysis of how different architectures handle noise and targeted perturbations after the fine-tuning process.

Methods

The authors adopted a standard transfer learning pipeline, as illustrated in their approach:

Figure 1: Pipeline of our Approach
  1. Selection: They chose three distinct architectures: ResNet50 (known for skip connections), DenseNet121 (known for dense connectivity), and MobileNet-V2 (optimized for mobile efficiency).
  2. Fine-tuning: Each model was fine-tuned for 60 epochs across four different datasets.
  3. Attacking: The fine-tuned models were subjected to three types of adversarial attacks:
  4. Fast Gradient Sign Method (FGSM): A fast, one-step attack that uses the gradient of the loss to perturb the image.
  5. Projected Gradient Descent (PGD): A more powerful, iterative version of FGSM.
  6. Random Uniform Gaussian: A baseline attack that simply adds random noise.
  7. Evaluation: The researchers measured "Adversarial Accuracy" across a range of perturbation strengths (epsilon values from 0.001 to 0.5).

Datasets

The study utilized four widely recognized image classification benchmarks:

  • MNIST: 70,000 grayscale images of handwritten digits (10 classes).
  • SVHN (Street View House Numbers): Over 99,000 images of house numbers cropped from Google Street View (10 classes).
  • CIFAR10: 60,000 color images across 10 general categories (e.g., birds, planes).
  • CIFAR100: Similar to CIFAR10 but with 100 classes, making it significantly more challenging.

Key Insights and Ideas

  • The Epsilon Sensitivity: Robustness is not a binary state. As the perturbation strength ($\epsilon$) increases, the model's accuracy drops predictably while the attack success rate climbs. This highlights that "robustness" is a sliding scale dependent on the expected noise in a real-world environment.
  • Architecture-Specific Strengths: The study found that MobileNet-V2 was surprisingly resilient on the MNIST dataset compared to its bulkier counterparts, suggesting that simpler architectures might sometimes hold an edge in specific, low-complexity domains.
  • Dataset Complexity vs. Robustness: There is a clear correlation between the difficulty of the dataset and the vulnerability of the model. All models struggled significantly more with CIFAR100 (where max adversarial accuracy hovered around 20-24%) compared to MNIST or SVHN.
  • Visual Deception: Even when an image looks virtually identical to a human after an FGSM attack, the model's internal logic can be completely derailed.
Figure 2: SVHN data with FGSM attack

Key Results

The quantitative results show a tug-of-war between clean accuracy and adversarial resilience:

  • Clean Performance: ResNet50 generally achieved the highest clean accuracy, peaking at 95.26% on SVHN and 92.44% on CIFAR10. DenseNet was the champion on MNIST with 99.66%.
  • Adversarial Resilience:
    • Under Random Gaussian noise, ResNet50 maintained a respectable 71.68% accuracy on SVHN, while DenseNet dropped to 26.82% on the same data.
  • On MNIST, MobileNet-V2 proved exceptionally tough to crack, maintaining 96.06% accuracy under FGSM attacks.
  • The PGD Impact: PGD proved to be a formidable foe. For MobileNet on MNIST, increasing epsilon from 0.0 to 0.5 caused adversarial accuracy to plummet from over 90% to roughly 69%.
Figure 3: Mobile-net with PGD attack for MNIST data Results

Detailed comparisons across all models and datasets can be seen in the evaluation tables:

Table 1: Evaluation on Clean Model

Limitations and Future Work

The authors noted several constraints that provide context for these results:

  • Computational Resources: Due to hardware limitations, the team could not evaluate every possible model architecture or fine-tuning hyperparameter.
  • Scope of Attacks: While three major attacks were covered, the landscape of adversarial machine learning is vast, and newer "black-box" or "adaptive" attacks were not explored.
  • Future Directions: The authors suggest exploring more advanced fine-tuning techniques, such as Robustness Critical Fine-Tuning (RiFT), and expanding the study to include even heavier models and larger-scale datasets to see if the observed trends hold.

Summary updated

Abstract

Our study systematically evaluates the robustness of fine-tuned pre-trained models across different datasets and attack types, aiming to provide insights for researchers in selecting pre-trained models for image classification tasks while prioritizing robustness against potential attacks. Our work explores the influence of fine-tuning pre-trained models with different datasets and attack types on their robustness and overview of the appropriate pre-trained model for image classification based on factors such as computation resources, memory usage, and accuracy on clean data. We fine-tune the models with weights. Evaluate the models on data before any attack and after different attack cases. The study utilizes publicly available image datasets such as MNIST, CIFAR10, CIFAR100, and SVHN to assess the robustness of pre-trained models. The results indicate that the robustness of fine-tuned models varies across different data distributions and sample sizes, emphasizing the need for tailored selection based on specific task requirements. The findings also highlight the varying performance of ResNet50, DenseNet, and MobileNet in defending against attacks on different datasets. Overall, this research provides valuable insights into the robustness of fine-tuned pre-trained models and their suitability for real-world applications in image classification.
BibTeX
@misc{john2026systematic,
  author = {Angela John and Hamayoon Behmanush},
  title = {{Systematic Evaluation of Robustness in Fine-tuned Models}},
  year = {2026},
  eprint = {2611.01900},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.01900},
}
Figure