摘要
在实际的隐写分析应用场景中,待测隐写算法大多是未知的,难以获得足量带标记的样本,从而导致隐写算法失配问题.为提升在隐写算法未知且仅有少量标记图像时隐写分析的检测性能,提出新型隐写分析网络BTONet.首先,提出结合瓶颈注意力机制的改进SRNet,即BAMSRNet,作为BTONet的特征提取模块,从空间维度和通道维度对纹理区域进行关注,解决小样本环境下直接使用SRNet会导致检测性能不佳的问题,在带标记图像数量极少的情况下提取有辨识性的特征.然后,将正交投影损失和交叉熵损失有机结合,从特征和预测标签2个角度强化不同类别之间的正交性,提升分类模块的性能.最后,在隐写算法失配的情况下,将BTONet与4个经典空域深度隐写分析算法进行检测准确率、训练时长、测试时长和算法稳定性等方面的比较,并进行消融实验.实验结果表明:相较于目前先进的基于深度学习的隐写分析方法,BTONet在小样本环境下能够取得更优的检测性能,检测性能提升了1.02%~10.35%;同时取得了极佳的稳定性,将检测准确率方差降低至其他隐写算法的1/60~1/20.
In practical steganalysis applications,the steganographic algorithms under test are often un-known,making it challenging to obtain a sufficient number of labeled samples,leading to stegano-graphic algorithm misalignment issues.To enhance the detection performance of steganalysis when the steganographic algorithm is unknown and only a limited number of labeled images are available,a new steganalysis network,BTONet,is proposed.Firstly,an enhanced SRNet incorporating a bottleneck attention mechanism,referred to as BAMSRNet,serves as the feature extraction module of BTONet.BAMSRNet focuses on the texture area in both spatial and channel dimensions,addressing the limita-tions of directly using SRNet in scenarios with a limited number of labeled images to extract discrimi-native features.Secondly,an integration of orthogonal projection loss and cross-entropy loss is pro-posed to bolster the orthogonality between different categories from the perspectives of features and predicted labels,thereby enhancing the performance of the classification module.Finally,BTONet is evaluated against four well-established spatial domain deep steganalysis algorithms in terms of detec-tion accuracy,training time,testing time,and algorithm stability under steganographic algorithm mis-alignment conditions,alongside conducting ablation experiments.Experimental results indicate that,compared to current state-of-the-art deep learning-based steganalysis approaches,BTONet achieves superior detection performance in few-shot learning scenarios,with detection performance improve-ments ranging from 1.02%to 10.35%.Moreover,BTONet demonstrates exceptional stability by re-ducing the variance in detection accuracy to 1/60 to 1/20 of the compared steganography algorithms.
作者
赖鸣姝
翁韶伟
田华伟
LAI Mingshu;WENG Shaowei;TIAN Huawei(Department of Information Engineering,Beijing Institute of Graphic Communication,Beijing 102600,China;Fujian Provincial Key Laboratory of Big Data Mining and Applications,Fujian University of Technology,Fuzhou 350118,China;School of Computer Science and Mathematics,Fujian University of Technology,Fuzhou 350118,China;Research Centre of Public Security Information,People’s Public Security University of China,Beijing 100038,China)
出处
《北京交通大学学报》
CAS
CSCD
北大核心
2024年第2期90-101,共12页
JOURNAL OF BEIJING JIAOTONG UNIVERSITY
基金
国家自然科学基金(61972405,62071434,62262062,61872095)
福建省杰出青年科学基金(2020J06043)。
关键词
隐写分析
瓶颈注意力机制
正交投影损失
小样本学习
steganalysis
bottleneck attention mechanism
orthogonal projection loss
few-shot learning
