1-Lipschitz layers compared: Memory, speed, and certifiable robustness
Prach B, Brau F, Buttazzo G, Lampert C. 2024. 1-Lipschitz layers compared: Memory, speed, and certifiable robustness. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. CVPR: Conference on Computer Vision and Pattern Recognition, 24574–24583.
Download
No fulltext has been uploaded. References only!
[Published Version]
Conference Paper
| Published
| English
Author
Department
Abstract
The robustness of neural networks against input perturbations with bounded
magnitude represents a serious concern in the deployment of deep learning
models in safety-critical systems. Recently, the scientific community has
focused on enhancing certifiable robustness guarantees by crafting 1-Lipschitz
neural networks that leverage Lipschitz bounded dense and convolutional layers.
Although different methods have been proposed in the literature to achieve this
goal, understanding the performance of such methods is not straightforward,
since different metrics can be relevant (e.g., training time, memory usage,
accuracy, certifiable robustness) for different applications. For this reason,
this work provides a thorough theoretical and empirical comparison between
methods by evaluating them in terms of memory usage, speed, and certifiable
robust accuracy. The paper also provides some guidelines and recommendations to
support the user in selecting the methods that work best depending on the
available resources. We provide code at
https://github.com/berndprach/1LipschitzLayersCompared.
Publishing Year
Date Published
2024-06-01
Proceedings Title
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
Acknowledgement
This work was partially supported by project SERICS (PE00000014) under the MUR National Recovery and Resilience Plan funded by the European Union - NextGenerationEU.
Page
24574-24583
Conference
CVPR: Conference on Computer Vision and Pattern Recognition
IST-REx-ID
Cite this
Prach B, Brau F, Buttazzo G, Lampert C. 1-Lipschitz layers compared: Memory, speed, and certifiable robustness. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Computer Vision Foundation; 2024:24574-24583.
Prach, B., Brau, F., Buttazzo, G., & Lampert, C. (2024). 1-Lipschitz layers compared: Memory, speed, and certifiable robustness. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 24574–24583). Computer Vision Foundation.
Prach, Bernd, Fabio Brau, Giorgio Buttazzo, and Christoph Lampert. “1-Lipschitz Layers Compared: Memory, Speed, and Certifiable Robustness.” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 24574–83. Computer Vision Foundation, 2024.
B. Prach, F. Brau, G. Buttazzo, and C. Lampert, “1-Lipschitz layers compared: Memory, speed, and certifiable robustness,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 24574–24583.
Prach B, Brau F, Buttazzo G, Lampert C. 2024. 1-Lipschitz layers compared: Memory, speed, and certifiable robustness. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. CVPR: Conference on Computer Vision and Pattern Recognition, 24574–24583.
Prach, Bernd, et al. “1-Lipschitz Layers Compared: Memory, Speed, and Certifiable Robustness.” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Computer Vision Foundation, 2024, pp. 24574–83.