Evaluating Adversarial Attacks on Traffic Sign Classifiers beyond Standard Baselines
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915061107261440 |
|---|---|
| author | Pavlitska, Svetlana Müller, Leopold Zöllner, J. Marius |
| author_facet | Pavlitska, Svetlana Müller, Leopold Zöllner, J. Marius |
| contents | Adversarial attacks on traffic sign classification models were among the first successfully tried in the real world. Since then, the research in this area has been mainly restricted to repeating baseline models, such as LISA-CNN or GTSRB-CNN, and similar experiment settings, including white and black patches on traffic signs. In this work, we decouple model architectures from the datasets and evaluate on further generic models to make a fair comparison. Furthermore, we compare two attack settings, inconspicuous and visible, which are usually regarded without direct comparison. Our results show that standard baselines like LISA-CNN or GTSRB-CNN are significantly more susceptible than the generic ones. We, therefore, suggest evaluating new attacks on a broader spectrum of baselines in the future. Our code is available at \url{https://github.com/KASTEL-MobilityLab/attacks-on-traffic-sign-recognition/}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_09150 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Evaluating Adversarial Attacks on Traffic Sign Classifiers beyond Standard Baselines Pavlitska, Svetlana Müller, Leopold Zöllner, J. Marius Computer Vision and Pattern Recognition Machine Learning Adversarial attacks on traffic sign classification models were among the first successfully tried in the real world. Since then, the research in this area has been mainly restricted to repeating baseline models, such as LISA-CNN or GTSRB-CNN, and similar experiment settings, including white and black patches on traffic signs. In this work, we decouple model architectures from the datasets and evaluate on further generic models to make a fair comparison. Furthermore, we compare two attack settings, inconspicuous and visible, which are usually regarded without direct comparison. Our results show that standard baselines like LISA-CNN or GTSRB-CNN are significantly more susceptible than the generic ones. We, therefore, suggest evaluating new attacks on a broader spectrum of baselines in the future. Our code is available at \url{https://github.com/KASTEL-MobilityLab/attacks-on-traffic-sign-recognition/}. |
| title | Evaluating Adversarial Attacks on Traffic Sign Classifiers beyond Standard Baselines |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2412.09150 |