Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Lyu, Saiyue"'
We propose Adaptive Randomized Smoothing (ARS) to certify the predictions of our test-time adaptive models against adversarial examples. ARS extends the analysis of randomized smoothing using $f$-Differential Privacy to certify the adaptive compositi
Externí odkaz:
http://arxiv.org/abs/2406.10427
Diffusion models (DMs) are one of the most widely used generative models for producing high quality images. However, a flurry of recent papers points out that DMs are least private forms of image generators, by extracting a significant number of near
Externí odkaz:
http://arxiv.org/abs/2305.15759
Diffusion models (DMs) are widely used for generating high-quality image datasets. However, since they operate directly in the high-dimensional pixel space, optimization of DMs is computationally expensive, requiring long training times. This contrib
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ec4e863e970ab125b400c970c2822cce
http://arxiv.org/abs/2305.15759
http://arxiv.org/abs/2305.15759