Generating Minimalist Adversarial Perturbations to Test Object-Detection Models: An Adaptive Multi-Metric Evolutionary Search Approach
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_ | 1866910424272732160 |
|---|---|
| author | McIntyre-Garcia, Cristopher Heymans, Adrien Borali, Beril Lee, Won-Sook Nejati, Shiva |
| author_facet | McIntyre-Garcia, Cristopher Heymans, Adrien Borali, Beril Lee, Won-Sook Nejati, Shiva |
| contents | Deep Learning (DL) models excel in computer vision tasks but can be susceptible to adversarial examples. This paper introduces Triple-Metric EvoAttack (TM-EVO), an efficient algorithm for evaluating the robustness of object-detection DL models against adversarial attacks. TM-EVO utilizes a multi-metric fitness function to guide an evolutionary search efficiently in creating effective adversarial test inputs with minimal perturbations. We evaluate TM-EVO on widely-used object-detection DL models, DETR and Faster R-CNN, and open-source datasets, COCO and KITTI. Our findings reveal that TM-EVO outperforms the state-of-the-art EvoAttack baseline, leading to adversarial tests with less noise while maintaining efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_17020 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Generating Minimalist Adversarial Perturbations to Test Object-Detection Models: An Adaptive Multi-Metric Evolutionary Search Approach McIntyre-Garcia, Cristopher Heymans, Adrien Borali, Beril Lee, Won-Sook Nejati, Shiva Software Engineering Artificial Intelligence Deep Learning (DL) models excel in computer vision tasks but can be susceptible to adversarial examples. This paper introduces Triple-Metric EvoAttack (TM-EVO), an efficient algorithm for evaluating the robustness of object-detection DL models against adversarial attacks. TM-EVO utilizes a multi-metric fitness function to guide an evolutionary search efficiently in creating effective adversarial test inputs with minimal perturbations. We evaluate TM-EVO on widely-used object-detection DL models, DETR and Faster R-CNN, and open-source datasets, COCO and KITTI. Our findings reveal that TM-EVO outperforms the state-of-the-art EvoAttack baseline, leading to adversarial tests with less noise while maintaining efficiency. |
| title | Generating Minimalist Adversarial Perturbations to Test Object-Detection Models: An Adaptive Multi-Metric Evolutionary Search Approach |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2404.17020 |