{"type":"conference","language":[{"iso":"eng"}],"_id":"17426","citation":{"chicago":"Prach, Bernd, Fabio Brau, Giorgio Buttazzo, and Christoph Lampert. “1-Lipschitz Layers Compared: Memory, Speed, and Certifiable Robustness.” In <i>Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition</i>, 24574–83. Computer Vision Foundation, 2024.","apa":"Prach, B., Brau, F., Buttazzo, G., &#38; Lampert, C. (2024). 1-Lipschitz layers compared: Memory, speed, and certifiable robustness. In <i>Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition</i> (pp. 24574–24583). Computer Vision Foundation.","mla":"Prach, Bernd, et al. “1-Lipschitz Layers Compared: Memory, Speed, and Certifiable Robustness.” <i>Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition</i>, Computer Vision Foundation, 2024, pp. 24574–83.","short":"B. Prach, F. Brau, G. Buttazzo, C. Lampert, in:, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Computer Vision Foundation, 2024, pp. 24574–24583.","ama":"Prach B, Brau F, Buttazzo G, Lampert C. 1-Lipschitz layers compared: Memory, speed, and certifiable robustness. In: <i>Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition</i>. Computer Vision Foundation; 2024:24574-24583.","ieee":"B. Prach, F. Brau, G. Buttazzo, and C. Lampert, “1-Lipschitz layers compared: Memory, speed, and certifiable robustness,” in <i>Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition</i>, 2024, pp. 24574–24583.","ista":"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."},"abstract":[{"text":"The robustness of neural networks against input perturbations with bounded\r\nmagnitude represents a serious concern in the deployment of deep learning\r\nmodels in safety-critical systems. Recently, the scientific community has\r\nfocused on enhancing certifiable robustness guarantees by crafting 1-Lipschitz\r\nneural networks that leverage Lipschitz bounded dense and convolutional layers.\r\nAlthough different methods have been proposed in the literature to achieve this\r\ngoal, understanding the performance of such methods is not straightforward,\r\nsince different metrics can be relevant (e.g., training time, memory usage,\r\naccuracy, certifiable robustness) for different applications. For this reason,\r\nthis work provides a thorough theoretical and empirical comparison between\r\nmethods by evaluating them in terms of memory usage, speed, and certifiable\r\nrobust accuracy. The paper also provides some guidelines and recommendations to\r\nsupport the user in selecting the methods that work best depending on the\r\navailable resources. We provide code at\r\nhttps://github.com/berndprach/1LipschitzLayersCompared.","lang":"eng"}],"author":[{"last_name":"Prach","full_name":"Prach, Bernd","first_name":"Bernd","id":"2D561D42-C427-11E9-89B4-9C1AE6697425"},{"full_name":"Brau, Fabio","last_name":"Brau","first_name":"Fabio"},{"last_name":"Buttazzo","full_name":"Buttazzo, Giorgio","first_name":"Giorgio"},{"id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0001-8622-7887","full_name":"Lampert, Christoph","last_name":"Lampert","first_name":"Christoph"}],"date_published":"2024-06-01T00:00:00Z","oa_version":"Published Version","acknowledgement":"This work was partially supported by project SERICS (PE00000014) under the MUR National Recovery and Resilience Plan funded by the European Union - NextGenerationEU.\r\n","year":"2024","quality_controlled":"1","article_processing_charge":"No","page":"24574-24583","status":"public","department":[{"_id":"GradSch"},{"_id":"ChLa"}],"publication_status":"published","day":"01","publication":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","related_material":{"link":[{"url":"https://github.com/berndprach/1LipschitzLayersCompared","relation":"software"}]},"date_updated":"2024-08-19T06:22:29Z","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","month":"06","title":"1-Lipschitz layers compared: Memory, speed, and certifiable robustness","corr_author":"1","publisher":"Computer Vision Foundation","date_created":"2024-08-14T08:42:32Z","has_accepted_license":"1","conference":{"name":"CVPR: Conference on Computer Vision and Pattern Recognition"}}