Multitask Identity-Aware Image Steganography via Minimax Optimization
Not on the map. Why?
Abstract (arXiv)
High-capacity image steganography, aimed at concealing a secret image in a cover image, is a technique to preserve sensitive data, e.g., faces and fingerprints. Previous methods focus on the security during transmission and subsequently run a risk of privacy leakage after the restoration of secret images at the receiving end. To address this issue, we propose a framework, called Multitask Identity-Aware Image Steganography (MIAIS), to achieve direct recognition on container images without restoring secret images. The key issue of the direct recognition is to preserve identity information of secret images into container images and make container images look similar to cover images at the same time. Thus, we introduce a simple content loss to preserve the identity information, and design a minimax optimization to deal with the contradictory aspects. We demonstrate that the robustness results can be transferred across different cover datasets. In order to be flexible for the secret image restoration in some cases, we incorporate an optional restoration network into our method, providing a multitask framework. The experiments under the multitask scenario show the effectiveness of our framework compared with other visual information hiding methods and state-of-the-art high-capacity image steganography methods.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 30 of its 80 references that are in the map. First posted on arXiv 13 Jul 2021.
Builds on
30 of 80 references.
References · 30
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
- 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
- 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
- 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
- 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
- 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 683
- 2018HiDDeN: Hiding Data With Deep Networkscited by 397
- 2019SteganoGAN: High Capacity Image Steganography with GANscited by 72
- 2019Drop to Adapt: Learning Discriminative Features for Unsupervised Domain Adaptationcited by 62
- 2017Generating Steganographic Images via Adversarial Trainingcited by 58
- 2017CryptoDL: Deep Neural Networks over Encrypted Datacited by 56
18 more
- 2016Defeating Image Obfuscation with Deep Learningcited by 43
- 2018Encryption-then-Compression Systems using Grayscale-based Image Encryption for JPEG Imagescited by 34
- 2018Learnable Image Encryptioncited by 33
- 2020Block-wise Scrambled Image Recognition Using Adaptation Networkcited by 27
- 2014StegExpose - A Tool for Detecting LSB Steganographycited by 25
- 2017Steganographic Generative Adversarial Networkscited by 21
- 2018Invisible Steganography via Generative Adversarial Networkscited by 21
- 2018Yedrouj-Net: An efficient CNN for spatial steganalysiscited by 19
- 2019Privacy-Preserving Deep Neural Networks with Pixel-based Image Encryption Considering Data Augmentation in the Encrypted Domaincited by 19
- 2017SSGAN: Secure Steganography Based on Generative Adversarial Networkscited by 18
- 2017End-to-end Trained CNN Encode-Decoder Networks for Image Steganographycited by 18
- 2017Privacy-Preserving Visual Learning Using Doubly Permuted Homomorphic Encryptioncited by 14
- 2018StegNet: Mega Image Steganography Capacity with Deep Convolutional Networkcited by 14
- 2019CryptoNN: Training Neural Networks over Encrypted Datacited by 14
- 2013P3: Toward Privacy-Preserving Photo Sharingcited by 8
- 2019Privacy-Preserving Machine Learning Using EtC Imagescited by 3
- 2019HOG feature extraction from encrypted images for privacy-preserving machine learningcited by 2
- 2018Synchronized Detection and Recovery of Steganographic Messages with Adversarial Learningcited by 1
Built on by
Citing papers per year: 2023: 1; 2024: 1.
2 papers.