Hiding Images in Plain Sight: Deep Steganography

By Shumeet Baluja. Neural Information Processing Systems, 2017

661 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/d511567a87218a555a4cc662c42ee89f044a5852

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Dongdong Chen
2. Lu Yuan
3. Justin Johnson
4. Ning Yu
5. Mario Fritz
6. Jianwei Yang
7. Matthew Tancik
8. Li Fei-Fei

Citations in the corpus

• A Simple Baseline for StyleGAN Inversion (2021, methodology): “Figure 12 shows the visual comparison of our method with universal deep hiding (UDH) [40] and dependent deep hiding (DDH) [5].”
• E2Style: Improve the Efficiency and Effectiveness of StyleGAN Inversion (2021, methodology): “More importantly, the traditional steganography we use provides theoretical security, whereas UDH and DDH do not have it because they are both based on deep learning networks.”
• HiDDeN: Hiding Data With Deep Networks (2018, background): “In contrast to our work, neither of [21, 22] consider encoding robustness; their focus is on steganography whereas HiDDeN can be used for watermarking as well.”
• Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data (2020, methodology): “Recent works replace hand-crafted hiding procedures with neural network encoding [4, 18, 45, 58, 55, 42, 33].”
• SteganoGAN: High Capacity Image Steganography with GANs (2019, methodology): “With the advent of deep learning in the past decade, a new class of image steganography approaches is emerging (Hayes & Danezis, 2017; Baluja, 2017; Zhu et al., 2018).”
• StegaStamp: Invisible Hyperlinks in Physical Photographs (2019, methodology): “Using a test set comprised of the cellphone camera + consumer printer combination, we compare variants of our method (described further in Section 5.3) to Baluja [5], HiD-DeN [54], and LFM [44] in Figure 6.”
• HiNet: Deep Image Hiding by Invertible Network (2021, background): “Baluja [4, 5] firstly proposed to hide a whole color image within another one using deep neural networks.”
• Robust Invisible Video Watermarking with Attention (2019, background): “Recently Convolutional Neural Networks (CNN) and Deep Learning (DL) have been used for image steganography [4] – suggesting that they may also be suitable for watermarking.”