计算机科学
隐写术
人工智能
语音识别
人工神经网络
模式识别(心理学)
计算机视觉
噪音(视频)
音频信号处理
信号处理
变换编码
作者
Y Li,Qiyang Xiao,Mingxi Zhang,Yanzhen Ren,Lina Wang
标识
DOI:10.1109/tifs.2026.3694658
摘要
Neural network–based steganography has garnered considerable attention for its strong security. However, existing approaches often suffer from excessive coupling between the embedding and extraction networks: the sender and receiver must employ paired models and maintain strict synchronization. Such synchronization not only complicates deployment but also introduces more severe potential risks of information leakage. To overcome this limitation, we propose a synchronization-free steganographic framework based on decoupled neural embedding networks, following the destruction–restoration principle. In our design, message embedding is realized through a destruction operation, while recovery is achieved using a neural network from the audio restoration domain. This decoupled architecture allows the sender to upgrade, replace, or randomize the embedding network—thus enabling dynamic model changes—without impairing the receiver’s ability to correctly extract the hidden message. As a result, synchronization-related vulnerabilities are fundamentally eliminated. Experimental results demonstrate that even under dynamic changes in the embedding network, the hidden information can still be reliably extracted, confirming both the effectiveness and enhanced security of the proposed approach.
科研通智能强力驱动
Strongly Powered by AbleSci AI