神经压缩潜表示中的图像数据隐藏
Image Data Hiding in Neural Compressed Latent Representations
AI总结:
本研究提出一种在通用神经压缩器潜表示中嵌入提取秘密的端到端可学习图像数据隐藏框架,结合感知损失与自研编解码实现高质高准确率,在压缩域保密性、鲁棒性及50倍以上的嵌入速度提升上表现优异,为神经压缩技术及应用提供新思路。
摘要:
我们提出了一种端到端可学习的图像数据隐藏框架,该框架在通用神经压缩器的潜表示中嵌入并提取秘密信息。通过结合感知损失函数与我们提出的消息编码器和解码器,该方法同时实现了高图像质量和高位准确率。与现有技术相比,我们的框架在压缩域中具备更优的图像保密性和具备竞争力的水印鲁棒性,同时嵌入速度提升了50倍以上。这些结果证明了结合数据隐藏技术与神经压缩的潜力,也为开发神经压缩技术及其应用提供了新的见解。
英文摘要:
We propose an end-to-end learned image data hiding framework that embeds and extracts secrets in the latent representations of a generic neural compressor. By leveraging a perceptual loss function in conjunction with our proposed message encoder and decoder, our approach simultaneously achieves high image quality and high bit accuracy. Compared to existing techniques, our framework offers superior image secrecy and competitive watermarking robustness in the compressed domain while accelerating the embedding speed by over 50 times. These results demonstrate the potential of combining data hiding techniques and neural compression and offer new insights into developing neural compression techniques and their applications.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。