A Statistical Method for Attack-Agnostic Adversarial Attack Detection with Compressive Sensing Comparison
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912625795792896 |
|---|---|
| author | Wimalasuriya, Chinthana Tragoudas, Spyros |
| author_facet | Wimalasuriya, Chinthana Tragoudas, Spyros |
| contents | Adversarial attacks present a significant threat to modern machine learning systems. Yet, existing detection methods often lack the ability to detect unseen attacks or detect different attack types with a high level of accuracy. In this work, we propose a statistical approach that establishes a detection baseline before a neural network's deployment, enabling effective real-time adversarial detection. We generate a metric of adversarial presence by comparing the behavior of a compressed/uncompressed neural network pair. Our method has been tested against state-of-the-art techniques, and it achieves near-perfect detection across a wide range of attack types. Moreover, it significantly reduces false positives, making it both reliable and practical for real-world applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_02707 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Statistical Method for Attack-Agnostic Adversarial Attack Detection with Compressive Sensing Comparison Wimalasuriya, Chinthana Tragoudas, Spyros Cryptography and Security Computer Vision and Pattern Recognition Machine Learning Image and Video Processing Adversarial attacks present a significant threat to modern machine learning systems. Yet, existing detection methods often lack the ability to detect unseen attacks or detect different attack types with a high level of accuracy. In this work, we propose a statistical approach that establishes a detection baseline before a neural network's deployment, enabling effective real-time adversarial detection. We generate a metric of adversarial presence by comparing the behavior of a compressed/uncompressed neural network pair. Our method has been tested against state-of-the-art techniques, and it achieves near-perfect detection across a wide range of attack types. Moreover, it significantly reduces false positives, making it both reliable and practical for real-world applications. |
| title | A Statistical Method for Attack-Agnostic Adversarial Attack Detection with Compressive Sensing Comparison |
| topic | Cryptography and Security Computer Vision and Pattern Recognition Machine Learning Image and Video Processing |
| url | https://arxiv.org/abs/2510.02707 |