activity
20172021
most citedA multi-branch convolutional neural network for detecting double JPEG compression

22 citations · 22 across the 4 of their papers we have counts for

collaborators
Showing cs.MMShow all

6 papers · 1 filter

cs.MM2021

MCTSteg: A Monte Carlo Tree Search-based Reinforcement Learning Framework for Universal Non-additive Steganography

Xianbo Mo, Shunquan Tan, Bin Li +1

Recent research has shown that non-additive image steganographic frameworks effectively improve security performance through adjusting distortion distribution. However, as far as w…

cs.MM2019

CALPA-NET: Channel-pruning-assisted Deep Residual Network for Steganalysis of Digital Images

Shunquan Tan, Weilong Wu, Zilong Shao +3

Over the past few years, detection performance improvements of deep-learning based steganalyzers have been usually achieved through structure expansion. However, excessive expanded…

cs.MM2019

CNN-based Steganalysis and Parametric Adversarial Embedding: a Game-Theoretic Framework

Xiaoyu Shi, Benedetta Tondi, Bin Li +1

CNN-based steganalysis has recently achieved very good performance in detecting content-adaptive steganography. At the same time, recent works have shown that, by adopting an appro…

cs.MM2018

Identification of Deep Network Generated Images Using Disparities in Color Components

Haodong Li, Bin Li, Shunquan Tan +1

With the powerful deep network architectures, such as generative adversarial networks, one can easily generate photorealistic images. Although the generated images are not dedicate…

cs.MM2018

CNN Based Adversarial Embedding with Minimum Alteration for Image Steganography

Weixuan Tang, Bin Li, Shunquan Tan +2

Historically, steganographic schemes were designed in a way to preserve image statistics or steganalytic features. Since most of the state-of-the-art steganalytic methods employ a…

cs.MM2018

WISERNet: Wider Separate-then-reunion Network for Steganalysis of Color Images

Jishen Zeng, Shunquan Tan, Guangqing Liu +2

Until recently, deep steganalyzers in spatial domain have been all designed for gray-scale images. In this paper, we propose WISERNet (the wider separate-then-reunion network) for…