Seek-and-Hide: Adversarial Steganography via Deep Reinforcement Learning

The goal of image steganography is to hide a full-sized image, termed secret, into another, termed cover. Prior image steganography algorithms can conceal only one secret within one cover. In this paper, we propose an adaptive local image steganography (AdaSteg) system that allows for scale- and loc...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on pattern analysis and machine intelligence 2022-11, Vol.44 (11), p.7871-7884
Main Authors: Pan, Wenwen, Yin, Yanling, Wang, Xinchao, Jing, Yongcheng, Song, Mingli
Format: Article
Language:English
Subjects:
adversarial examples
Algorithms
Containers
Convolutional neural networks
Deep learning
Encryption
Location awareness
Machine learning
Receivers
Reinforcement learning
Steganography
Task analysis
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The goal of image steganography is to hide a full-sized image, termed secret, into another, termed cover. Prior image steganography algorithms can conceal only one secret within one cover. In this paper, we propose an adaptive local image steganography (AdaSteg) system that allows for scale- and location-adaptive image steganography. By adaptively hiding the secret on a local scale, the proposed system makes the steganography more secured, and further enables multi-secret steganography within one single cover. Specifically, this is achieved via two stages, namely the adaptive patch selection stage and secret encryption stage. Given a pair of secret and cover, first, the optimal local patch for concealment is determined adaptively by exploiting deep reinforcement learning with the proposed steganography quality function and policy network. The secret image is then converted into a patch of encrypted noises, resembling the process of generating adversarial examples, which are further encoded to a local region of the cover to realize a more secured steganography. Furthermore, we propose a novel criterion for the assessment of local steganography, and also collect a challenging dataset that is specialized for the task of image steganography, thus contributing to a standardized benchmark for the area. Experimental results demonstrate that the proposed model yields results superior to the state of the art in both security and capacity.
ISSN:0162-8828
1939-3539
2160-9292
DOI:10.1109/TPAMI.2021.3114555