"Break Our Steganographic System": The Ins and Outs of Organizing BOSS

By Patrick Bas, Tomáš Filler, Tomás Pevný. Information Hiding, 2011

1,282 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/5774f92bc2e7574a5309d95900cf24a8ea9d8a16

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Yedroudj-Net: An Efficient CNN for Spatial Steganalysis (2018, neutral): “For a fair comparison, all the involved steganalysis methods are tested on the same subsampled images from the BOSSBase database v.1.01 [22].”
Steganalysis of Adaptive JPEG Steganography Using 2D Gabor Filters (2015, methodology): “01 [1] are converted into JPEG image with quality factor 75, and then stego images are generated by JUNIWARD steganography which is a state-of-the-art hiding method in JPEG domain.”
Low-Complexity Features for JPEG Steganalysis Using Undecimated DCT (2015, positive): “01 [2] containing 10,000 grayscale 512 × 512 images.”
High Capacity Reversible Data Hiding in Encrypted Images by Patch-Level Sparse Representation (2016, methodology): “The images in BOSSBase are gray-levels with size 512 × 512.”
Deep Residual Network for Steganalysis of Digital Images (2019, background): “01 [3] and BOWS2 [4], each containing 10,000 grayscale images re-”
Depth-Wise Separable Convolutions and Multi-Level Pooling for an Efficient Spatial CNN-Based Steganalysis (2020, background): “01 [33] consisting of 10,000 grey-level images of size 512×512, never compressed, and coming from 7 different cameras.”
Selection-channel-aware rich model for Steganalysis of digital images (2014, methodology): “Modifying the latter approach to consider the knowledge of the selection channel is, however, not easy as witnessed by the futile effort of the BOSS competition participants [1] attacking HUGO.”
Median Filtering Forensics Based on Convolutional Neural Networks (2015, methodology): “These images are from five widely used image databases: the BOSSbase 1.01 [20], the UCID database [21], the BOSS RAW database [22], the Dresden Image Database [23] and the NRCS Photo Gallery database [24].”
A new cost function for spatial image steganography (2014, background): “01 database [15] with an amount of 10,000 gray-scale images with size 512 × 512 pixels.”
Deep learning for steganalysis via convolutional neural networks (2015, background): “01.(22) This database contains 10,000 images acquired by seven digital cameras in”
HiDDeN: Hiding Data With Deep Networks (2018, methodology): “We test all methods on 512 × 512 cover images from the BOSS dataset [31], which is a common testbed for steganography algorithms.”
A New Payload Partition Strategy in Color Image Steganography (2020, methodology): “The image set is obtained from the standard color BOSSBase image set [40], containing 10,000 full-resolution raw color images.”
Deep Learning Hierarchical Representations for Image Steganalysis (2017, methodology): “01 [12], which contains 10,000 512 × 512 × 8-bit grayscale”
Deep residual learning for image steganalysis (2018, methodology): “5 Sample images in the cropped BOSSbase dataset Table 1 Configurations for DRN models # conv.”