Steganographer Detection via Multiple-instance Learning Graph Convolutional Networks
Steganographer detection aims to solve the problem of illegal use of batch steganography by designing models to detect steganographers who embed secret information in images for covert communication.This paper proposes a novel steganographer detection algorithm called as multiple-instance learning graph convolutional net-work(MILGCN)to formalize steganography detection as a multiple-instance learning(MIL)task.The commonness enhancement graph convolutional network(GCN)and attention graph readout module designed in this paper can adaptively highlight the positive instance pattern and construct distinguishable bag representations for stegano-grapher detection.Experiments show that the designed model can successfully attack a variety of batch stegano-graphy and the corresponding strategies.
Image steganograher detectiongraph convolutional network(GCN)multiple-instance learning(MIL)bag of instances representation
万方数据
维普
