Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.03625 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915651242688512 |
|---|---|
| author | Yang, Zhigang Liu, Yuan Zhang, Jiawei Zhang, Puning Ma, Xinqiang |
| author_facet | Yang, Zhigang Liu, Yuan Zhang, Jiawei Zhang, Puning Ma, Xinqiang |
| contents | Although the remarkable performance of deep neural networks (DNNs) in image classification, their vulnerability to adversarial attacks remains a critical challenge. Most existing detection methods rely on complex and poorly interpretable architectures, which compromise interpretability and generalization. To address this, we propose FeatureLens, a lightweight framework that acts as a lens to scrutinize anomalies in image features. Comprising an Image Feature Extractor (IFE) and shallow classifiers (e.g., SVM, MLP, or XGBoost) with model sizes ranging from 1,000 to 30,000 parameters, FeatureLens achieves high detection accuracy ranging from 97.8% to 99.75% in closed-set evaluation and 86.17% to 99.6% in generalization evaluation across FGSM, PGD, CW, and DAmageNet attacks, using only 51 dimensional features. By combining strong detection performance with excellent generalization, interpretability, and computational efficiency, FeatureLens offers a practical pathway toward transparent and effective adversarial defense. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_03625 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FeatureLens: A Highly Generalizable and Interpretable Framework for Detecting Adversarial Examples Based on Image Features Yang, Zhigang Liu, Yuan Zhang, Jiawei Zhang, Puning Ma, Xinqiang Computer Vision and Pattern Recognition Although the remarkable performance of deep neural networks (DNNs) in image classification, their vulnerability to adversarial attacks remains a critical challenge. Most existing detection methods rely on complex and poorly interpretable architectures, which compromise interpretability and generalization. To address this, we propose FeatureLens, a lightweight framework that acts as a lens to scrutinize anomalies in image features. Comprising an Image Feature Extractor (IFE) and shallow classifiers (e.g., SVM, MLP, or XGBoost) with model sizes ranging from 1,000 to 30,000 parameters, FeatureLens achieves high detection accuracy ranging from 97.8% to 99.75% in closed-set evaluation and 86.17% to 99.6% in generalization evaluation across FGSM, PGD, CW, and DAmageNet attacks, using only 51 dimensional features. By combining strong detection performance with excellent generalization, interpretability, and computational efficiency, FeatureLens offers a practical pathway toward transparent and effective adversarial defense. |
| title | FeatureLens: A Highly Generalizable and Interpretable Framework for Detecting Adversarial Examples Based on Image Features |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.03625 |