# THInImg: Cross-modal Steganography for Presenting Talking Heads in Images

arXiv: https://arxiv.org/abs/2311.17177 · HTML: https://mlsanity.com/paper/2311.17177/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 51 references that are in the map.
- First posted on arXiv 28 Nov 2023.

## Builds on (most cited first, 29 of 29)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing](https://mlsanity.com/paper/2011.15126/) (2020)
- [HiDDeN: Hiding Data With Deep Networks](https://mlsanity.com/paper/1807.09937/) (2018)
- [MakeItTalk: Speaker-Aware Talking-Head Animation](https://mlsanity.com/paper/2004.12992/) (2020)
- [WaveGlow: A Flow-based Generative Network for Speech Synthesis](https://mlsanity.com/paper/1811.00002/) (2018)
- [StegaStamp: Invisible Hyperlinks in Physical Photographs](https://mlsanity.com/paper/1904.05343/) (2019)
- [Capture, Learning, and Synthesis of 3D Speaking Styles](https://mlsanity.com/paper/1905.03079/) (2019)
- [Hierarchical Cross-Modal Talking Face Generationwith Dynamic Pixel-Wise Loss](https://mlsanity.com/paper/1905.03820/) (2019)
- [Neural Voice Puppetry: Audio-driven Facial Reenactment](https://mlsanity.com/paper/1912.05566/) (2019)
- [Audio-Driven Emotional Video Portraits](https://mlsanity.com/paper/2104.07452/) (2021)
- [Guided Image Generation with Conditional Invertible Neural Networks](https://mlsanity.com/paper/1907.02392/) (2019)
- [You said that?](https://mlsanity.com/paper/1705.02966/) (2017)
- [Invertible Image Signal Processing](https://mlsanity.com/paper/2103.15061/) (2021)
- [Audio-driven Talking Face Video Generation with Learning-based Personalized Head Pose](https://mlsanity.com/paper/2002.10137/) (2020)
- [Invertible Image Rescaling](https://mlsanity.com/paper/2005.05650/) (2020)
- [Talking Face Generation by Conditional Recurrent Adversarial Network](https://mlsanity.com/paper/1804.04786/) (2018)
- [Everybody's Talkin': Let Me Talk as You Want](https://mlsanity.com/paper/2001.05201/) (2020)
- [SteganoGAN: High Capacity Image Steganography with GANs](https://mlsanity.com/paper/1901.03892/) (2019)
- [Stochastic Image-to-Video Synthesis using cINNs](https://mlsanity.com/paper/2105.04551/) (2021)
- [CNN Based Adversarial Embedding with Minimum Alteration for Image Steganography](https://mlsanity.com/paper/1803.09043/) (2018)
- [Large-capacity and Flexible Video Steganography via Invertible Neural Network](https://mlsanity.com/paper/2304.12300/) (2023)
- [Compressing Video Calls using Synthetic Talking Heads](https://mlsanity.com/paper/2210.03692/) (2022)
- [Txt2Vid: Ultra-Low Bitrate Compression of Talking-Head Videos via Text](https://mlsanity.com/paper/2106.14014/) (2021)
- [Multi-Stage Residual Hiding for Image-into-Audio Steganography](https://mlsanity.com/paper/2101.01872/) (2021)
- [Hide and Speak: Towards Deep Neural Networks for Speech Steganography](https://mlsanity.com/paper/1902.03083/) (2019)
- [Heard More Than Heard: An Audio Steganography Method Based on GAN](https://mlsanity.com/paper/1907.04986/) (2019)
- [Deep Neural Networks based Invisible Steganography for Audio-into-Image Algorithm](https://mlsanity.com/paper/2102.09173/) (2021)
- [Extreme-scale Talking-Face Video Upsampling with Audio-Visual Priors](https://mlsanity.com/paper/2208.08118/) (2022)

## Built on by (most cited first, 6 of 6)

- [Images that Sound: Composing Images and Sounds on a Single Canvas](https://mlsanity.com/paper/2405.12221/) (2024)
- [Staying VIGILant: Mitigating Visual Laziness via Counterfactual Visual Alignment in MLLMs](https://mlsanity.com/paper/2606.26387/) (2026)
- [Rethinking Layer-Wise Information Allocation for Vision Foundation Model Adaptation](https://mlsanity.com/paper/2607.21973/) (2026)
- [Dynamic Hub-and-Spoke Memory for Streaming Video Understanding](https://mlsanity.com/paper/2608.30294/) (2026)
- [Layer-Specific Prompt Fusion Discovery via Differentiable Search in Vision Foundation Models](https://mlsanity.com/paper/2606.26379/) (2026)
- [Adapting Vision Foundation Models with Cascaded Semantics](https://mlsanity.com/paper/2608.05393/) (2026)

## Abstract (arXiv)

Cross-modal Steganography is the practice of concealing secret signals in publicly available cover signals (distinct from the modality of the secret signals) unobtrusively. While previous approaches primarily concentrated on concealing a relatively small amount of information, we propose THInImg, which manages to hide lengthy audio data (and subsequently decode talking head video) inside an identity image by leveraging the properties of human face, which can be effectively utilized for covert communication, transmission and copyright protection. THInImg consists of two parts: the encoder and decoder. Inside the encoder-decoder pipeline, we introduce a novel architecture that substantially increase the capacity of hiding audio in images. Moreover, our framework can be extended to iteratively hide multiple audio clips into an identity image, offering multiple levels of control over permissions. We conduct extensive experiments to prove the effectiveness of our method, demonstrating that THInImg can present up to 80 seconds of high quality talking-head video (including audio) in an identity image with 160x160 resolution.