NNID : Nearly Nested Image Datasets Webpage published in October 2022. Send an email to to get a private copy. HOW TO CITE the NNID database: " A study on the invariance in security whatever the dimension of images for the steganalysis by deep-learning ”, Kévin Planolles, Marc Chaumont, Frédéric Comby, IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP’2023, 4-10 June 2023, Greek island of Rhodes, Rhodes, 5 pages. Paper (pdf). Slides (pdf). Poster (pdf). Video (mp4). FAQ (pdf). https://github.com/Kevin-Planolles/steganalysis_with_CNN_dilated-Yedroudj-Net GitHub of the Dilated-Yedroudj-Net : https://github.com/Kevin-Planolles/steganalysis_with_CNN_dilated-Yedroudj-Net  Relative payload size (bpp) for an embedding with UNIWARD |