摘要
本文提出一种基于跨模态学习的鲁棒文本隐写方法,通过生成与图像语义一致的语句进行秘密信息的嵌入。将图像的语义特征与区域特征融合,提高文本的生成质量,并在训练阶段设计一个随机丢词的攻击层,进一步提高了隐写文本的鲁棒性。在实验部分,从抗文本攻击和抗图像攻击两个方面验证了所提出方法的鲁棒性。结果表明,所提出的隐写方法在文本生成质量与鲁棒性方面均获得了较好的性能,有效提升了隐写文本的认知隐蔽性。
This paper proposes a robust text steganography method based on cross-modal learning,embedding secret information by generating sentences consistent with the semantics of image.To improve text generation quality,both semantic and regional features of the image are integrated.Moreover,a random word deletion attack layer is designed during training to further enhance the robustness of the steganographic texts.Experiments evaluate the model’s robustness against both text and image attack.The results demonstrate that the proposed method achieves superior text generation quality and robustness,effectively improving the cognitive concealment of steganographic text.
作者
马婷
谭云
秦姣华
向旭宇
MA Ting;TAN Yun;QIN Jiaohua;XIANG Xuyu(School of Electronics,Information,and Physics,Central South University of Forestry and Technology,Changsha 410004,Hunan,China;School of Computer Science and Mathematics,Central South University of Forestry and Technology,Changsha 410004,Hunan,China)
出处
《应用科学学报》
北大核心
2025年第3期403-414,共12页
Journal of Applied Sciences
基金
湖南省自然科学基金项目(No.2025JJ50743)
湖南省教育厅科学研究项目(No.24A0196)。
关键词
隐写
生成式文本隐写
跨模态
鲁棒性
steganography
generative text steganography
cross-modal
robustness
