HiDDeN: Hiding Data With Deep Networks

By Jiren Zhu, Russell Kaplan, Justin Johnson, Li Fei-Fei. European Conference on Computer Vision, 2018

1,192 citations recorded by the source corpus.

Recent work has shown that deep neural networks are highly sensitive to tiny perturbations of input images, giving rise to adversarial examples. Though this property is usually considered a weakness of learned models, we explore whether it can be beneficial. We find that neural networks can learn to use invisible perturbations to encode a rich amount of useful information. In fact, one can exploit this capability for the task of data hiding. We jointly train encoder and decoder networks, where given an input message and cover image, the encoder produces a visually indistinguishable encoded image, from which the decoder can recover the original message. We show that these encodings are competitive with existing data hiding algorithms, and further that they can be made robust to noise: our models learn to reconstruct hidden information in an encoded image despite the presence of Gaussian blurring, pixel-wise dropout, cropping, and JPEG compression. Even though JPEG is non-differentiable, we show that a robust model can be trained using differentiable approximations. Finally, we demonstrate that adversarial training improves the visual quality of encoded images.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/a4c4c865ed31d88df7458e9f19db54f766f042a1

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

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).”
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].”
Distortion Agnostic Deep Watermarking (2020, methodology): “However, training on a speciﬁc image distortion can easily lead to overﬁtting, and generalize poorly across other types of distortions [45].”
Robust Invisible Video Watermarking with Attention (2019, methodology): “…of attention-based architectures for data hiding tasks such as steganography and watermarking which is superior to existing approaches such as [32] as it (1) uses less memory, (2) is easier to train, and (3) is robust against common video processing operations such as scaling, cropping, and…”
HiNet: Deep Image Hiding by Invertible Network (2021, methodology): “To verify the effectiveness of our method, we compare it with several state-of-the-art (SOTA) image hiding methods, including one traditional image steganography method named 4bit-LSB, and three deep learning based methods: HiDDeN [41], Weng et al.”
MBRS: Enhancing Robustness of DNN-based Watermarking by Mini-Batch of Real and Simulated JPEG Compression (2021, methodology): “Our baseline for comparison are [27], [17] and [22].”
Invisible Backdoor Attack with Sample-Specific Triggers (2020, methodology): “Specifically, inspired by DNN-based image steganography [2, 51, 39], we generate sample-specific invisible additive noises as backdoor triggers by encoding an attacker-specified string into benign images through an encoder-decoder network.”
Radioactive data: tracing through training (2020, positive): “This observation has motivated several authors to employ convnets to watermark images (Vukotić et al., 2018; Zhu et al., 2018) by inserting marks in this latent space.”
StegaStamp: Invisible Hyperlinks in Physical Photographs (2019, methodology): “HiDDeN [54] uses pixelwise perturbations along with random masking.”
ReDMark: Framework for residual diffusion watermarking based on deep networks (2018, methodology): “The authors of HiDDeN framework [27] use COCO [49] for their experiments.”
A Watermark for Large Language Models (2023, neutral): “Watermarking is considered easier for continuous-valued data, where watermarks can be encoded with a variety of well-studied strategies (Petitcolas et al., 1999; Zhu et al., 2018; Lu et al., 2021; Boenisch, 2021).”
The Stable Signature: Rooting Watermarks in Latent Diffusion Models (2023, positive): “We use HiDDeN [108], a classical method in the deep watermarking literature.”