Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2406.10090 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912769627914240 |
|---|---|
| author | Gupta, Srishti Chen, Zhang Demetrio, Luca Feng, Xiaoyi Xia, Zhaoqiang Cinà, Antonio Emanuele Pintor, Maura Oneto, Luca Demontis, Ambra Biggio, Battista Roli, Fabio |
| author_facet | Gupta, Srishti Chen, Zhang Demetrio, Luca Feng, Xiaoyi Xia, Zhaoqiang Cinà, Antonio Emanuele Pintor, Maura Oneto, Luca Demontis, Ambra Biggio, Battista Roli, Fabio |
| contents | Thanks to their extensive capacity, over-parameterized neural networks exhibit superior predictive capabilities and generalization. However, having a large parameter space is considered one of the main suspects of the neural networks' vulnerability to adversarial example -- input samples crafted ad-hoc to induce a desired misclassification. Relevant literature has claimed contradictory remarks in support of and against the robustness of over-parameterized networks. These contradictory findings might be due to the failure of the attack employed to evaluate the networks' robustness. Previous research has demonstrated that depending on the considered model, the algorithm employed to generate adversarial examples may not function properly, leading to overestimating the model's robustness. In this work, we empirically study the robustness of over-parameterized networks against adversarial examples. However, unlike the previous works, we also evaluate the considered attack's reliability to support the results' veracity. Our results show that over-parameterized networks are robust against adversarial attacks as opposed to their under-parameterized counterparts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_10090 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Over-parameterization and Adversarial Robustness in Neural Networks: An Overview and Empirical Analysis Gupta, Srishti Chen, Zhang Demetrio, Luca Feng, Xiaoyi Xia, Zhaoqiang Cinà, Antonio Emanuele Pintor, Maura Oneto, Luca Demontis, Ambra Biggio, Battista Roli, Fabio Machine Learning 68T10 I.5 Thanks to their extensive capacity, over-parameterized neural networks exhibit superior predictive capabilities and generalization. However, having a large parameter space is considered one of the main suspects of the neural networks' vulnerability to adversarial example -- input samples crafted ad-hoc to induce a desired misclassification. Relevant literature has claimed contradictory remarks in support of and against the robustness of over-parameterized networks. These contradictory findings might be due to the failure of the attack employed to evaluate the networks' robustness. Previous research has demonstrated that depending on the considered model, the algorithm employed to generate adversarial examples may not function properly, leading to overestimating the model's robustness. In this work, we empirically study the robustness of over-parameterized networks against adversarial examples. However, unlike the previous works, we also evaluate the considered attack's reliability to support the results' veracity. Our results show that over-parameterized networks are robust against adversarial attacks as opposed to their under-parameterized counterparts. |
| title | Over-parameterization and Adversarial Robustness in Neural Networks: An Overview and Empirical Analysis |
| topic | Machine Learning 68T10 I.5 |
| url | https://arxiv.org/abs/2406.10090 |