Intriguing properties of input-dependent randomized smoothing

conference paper Intriguing properties of input-dependent randomized smoothing published yes Peter Súkeník author d64d6a8d-eb8e-11eb-b029-96fd216dec3c Aleksei Kuvshinov author Stephan Günnemann author ICML: International Conference on Machine Learning Randomized smoothing is currently considered the state-of-the-art method to obtain certifiably robust classifiers. Despite its remarkable performance, the method is associated with various serious problems such as “certified accuracy waterfalls”, certification vs. accuracy trade-off, or even fairness issues. Input-dependent smoothing approaches have been proposed with intention of overcoming these flaws. However, we demonstrate that these methods lack formal guarantees and so the resulting certificates are not justified. We show that in general, the input-dependent smoothing suffers from the curse of dimensionality, forcing the variance function to have low semi-elasticity. On the other hand, we provide a theoretical and practical framework that enables the usage of input-dependent smoothing even in the presence of the curse of dimensionality, under strict restrictions. We present one concrete design of the smoothing variance function and test it on CIFAR10 and MNIST. Our design mitigates some of the problems of classical smoothing and is formally underlined, yet further improvement of the design is still necessary. https://research-explorer.ista.ac.at/download/12664/12665/sukeni-k22a.pdf application/pdfno ML Research Press2022Baltimore, MD, United States eng Proceedings of the 39th International Conference on Machine Learning 2110.05365 16220697-20743 Súkeník P, Kuvshinov A, Günnemann S. Intriguing properties of input-dependent randomized smoothing. In: Proceedings of the 39th International Conference on Machine Learning. Vol 162. ML Research Press; 2022:20697-20743. P. Súkeník, A. Kuvshinov, S. Günnemann, in:, Proceedings of the 39th International Conference on Machine Learning, ML Research Press, 2022, pp. 20697–20743. Súkeník P, Kuvshinov A, Günnemann S. 2022. Intriguing properties of input-dependent randomized smoothing. Proceedings of the 39th International Conference on Machine Learning. ICML: International Conference on Machine Learning vol. 162, 20697–20743. Súkeník, P., Kuvshinov, A., & Günnemann, S. (2022). Intriguing properties of input-dependent randomized smoothing. In Proceedings of the 39th International Conference on Machine Learning (Vol. 162, pp. 20697–20743). Baltimore, MD, United States: ML Research Press. Súkeník, Peter, Aleksei Kuvshinov, and Stephan Günnemann. “Intriguing Properties of Input-Dependent Randomized Smoothing.” In Proceedings of the 39th International Conference on Machine Learning, 162:20697–743. ML Research Press, 2022. P. Súkeník, A. Kuvshinov, and S. Günnemann, “Intriguing properties of input-dependent randomized smoothing,” in Proceedings of the 39th International Conference on Machine Learning, Baltimore, MD, United States, 2022, vol. 162, pp. 20697–20743. Súkeník, Peter, et al. “Intriguing Properties of Input-Dependent Randomized Smoothing.” Proceedings of the 39th International Conference on Machine Learning, vol. 162, ML Research Press, 2022, pp. 20697–743. 126642023-02-20T08:30:21Z2025-07-10T11:50:28Z