1. <Large-capacity Image Steganography Based on Invertible Neural Networks>CVPR2021;可逆網(wǎng)絡(luò)ISN，大容量的實(shí)現(xiàn)是靠RGB通道的累加；無公開代碼
2. <Multitask Identity-Aware Image Steganography via Minimax Optimization>IEEE Transactions on Image Processing2021;提出直接識(shí)別防止接收端泄密、其中恢復(fù)分支可選；主要涉及身份信息;有公開代碼GitHub - jiabaocui/MIAIS
3. <HiNet: Deep Image Hiding by Invertible Network>ICCV2021;可逆網(wǎng)絡(luò)HiNet；與ISN同期首次在圖像隱藏運(yùn)用可逆網(wǎng)絡(luò)，未實(shí)現(xiàn)大容量以及串聯(lián)分階段隱藏，強(qiáng)調(diào)可逆網(wǎng)絡(luò)的性能優(yōu)勢;有公開代碼GitHub - TomTomTommi/HiNet: Official PyTorch implementation of "HiNet: Deep Image Hiding by Invertible Network" (ICCV 2021)
4. <Breaking Robust Data Hiding in Online Social Networks>IEEE Signal Processing Letters 2022;隱寫分析；OSN背景（FUDAN）；不需要原始載體圖像，直接輸入隱寫圖像，輸出質(zhì)量略有提升的載體圖像；三個(gè)模塊分別：去除隱藏的秘密數(shù)據(jù)、增強(qiáng)圖像質(zhì)量和提高整體性能;無公開代碼
5. <Image Generation Network for Covert Transmission in Online Social Network>ACMMM2022;圖像隱寫，OSN背景（FUDAN）；無覆蓋式（沒載體圖），生成模塊 對(duì)抗模塊 提取模塊 噪聲模塊，輸入秘密和目標(biāo)表情，生成含有秘密的表情包人臉圖;無工開代碼
6. <Robust Invertible Image Steganography>CVPR2022;可逆網(wǎng)絡(luò) 強(qiáng)調(diào)魯棒； 魯棒靠載體增強(qiáng)模塊實(shí)現(xiàn)（消除收到的載密圖像噪聲以及JPEG壓縮失真的影響）；無公開代碼
7. <Image Disentanglement Autoencoder for Steganography Without Embedding>CVPR2022;無嵌入生成隱寫 解糾纏自動(dòng)編碼器，直接生成stego，不需要載體圖像，分成結(jié)構(gòu)和紋理兩種表示，并用結(jié)構(gòu)紋理的多種組合形成多種隱寫圖像，再提取結(jié)構(gòu)信息恢復(fù)秘密;有公開代碼GitHub - Lemok00/IDEAS: Official pytorch implementation of paper "Image Disentanglement Autoencoder for Steganography without Embedding" (CVPR2022).
8. <Fixed Neural Network Steganography: Train The Images, Not The Network>ICLR2022;FNNS 是在steganoGAN上的改進(jìn)；主要強(qiáng)調(diào)降低解碼錯(cuò)誤率：在3bpp的情況下實(shí)現(xiàn)精確的0%錯(cuò)誤率;有代碼GitHub - varshakishore/FNNS
9. <Generative Steganography Network>ACMMM2022;無嵌入生成隱寫：根據(jù)輸入對(duì)（潛在向量和噪聲/秘密信息）不同，可選擇生成cover還是stego;無公開代碼
10. <StegGAN: hiding image within image using conditional generative adversarial networks>Multimedia Tools and Applications2022;有公開代碼GitHub - brijeshiitg/StegGAN
11. <Large-capacity and Flexible Video Steganography via Invertible Neural Network>CVPR2023;視頻隱寫；可以在一個(gè)載體視頻中隱藏最多7個(gè)秘密視頻；提出一種秘鑰可控方案；多視頻隱藏可變數(shù)量方案;有代碼Large-capacity and Flexible Video Steganography via Invertible Neural Network | Papers With Code
12. <DeepMIH: Deep Invertible Network for Multiple Image Hiding>TPAMI2023;可逆網(wǎng)絡(luò)hinet升級(jí)版，強(qiáng)調(diào)串聯(lián)多圖像隱藏，有imp模塊引導(dǎo)第二次嵌入；有感知損失；做了頻域子帶分離試驗(yàn)，結(jié)論是高頻子帶適合隱藏信息;有代碼，和hinet一個(gè)作者主頁
13. <SteganoGAN: High Capacity Image Steganography with GANs>2019;Jupiter； 解碼器 編碼器 判別器;有代碼SteganoGAN: High Capacity Image Steganography with GANs | Papers With Code
14. ?<HiDDeN: Hiding Data With Deep Networks>2018ECCV;代碼：GitHub - ando-khachatryan/HiDDeN: Pytorch implementation of paper "HiDDeN: Hiding Data With Deep Networks" by Jiren Zhu, Russell Kaplan, Justin Johnson, and Li Fei-Fei

15. <RoSteALS: Robust Steganography using Autoencoder Latent Space>2023CVPR;針對(duì)現(xiàn)有方法因?yàn)楸ＷC圖像質(zhì)量和抗擾動(dòng)魯棒性導(dǎo)致的訓(xùn)練復(fù)雜的問題，提出了一種凍結(jié)預(yù)訓(xùn)練編碼器的訓(xùn)練簡單的輕量級(jí)網(wǎng)絡(luò)。GitHub - TuBui/RoSteALS: RoSteALS: Robust Steganography using Autoencoder Latent Space文章來源地址http://www.zghlxwxcb.cn/news/detail-845810.html

16. <Towards Robust Data Hiding Against (JPEG) Compression: A Pseudo-Differentiable Deep Learning Approach>2020;針對(duì)(jpeg)壓縮的穩(wěn)健數(shù)據(jù)隱藏:一種偽可微深度學(xué)習(xí)方法mikolez/Robust_JPEG · GitHub
17. <Robust Image Steganography: Hiding Messages in Frequency Coefficients>2023AAAI;基于INN的魯棒隱寫方法；尤其是針對(duì)JPEG壓縮具有良好魯棒性；秘密信息形式為二進(jìn)制；無公開代碼
18. <MBRS：Enhancing Robustness of DNN-based Watermarking by Mini-Batch of Real and Simulated JPEG>MM '21;對(duì)于不同的小批量，隨機(jī)選擇真實(shí)JPEG、模擬JPEG和無噪聲層中的一個(gè)作為噪聲層；魯棒方法；有代碼jzyustc/MBRS: This is the source code of paper MBRS : Enhancing Robustness of DNN-based Watermarking by Mini-Batch of Real and Simulated JPEG Compression, which is received by ACM MM' 21. (github.com)

到了這里，關(guān)于【論文閱讀】圖像信息隱藏文章匯總（含代碼）的文章就介紹完了。如果您還想了解更多內(nèi)容，請(qǐng)?jiān)谟疑辖撬阉鱐OY模板網(wǎng)以前的文章或繼續(xù)瀏覽下面的相關(guān)文章，希望大家以后多多支持TOY模板網(wǎng)！