tracycuiq / learning-image-steganography

List for learning image steganography

Learning Image Steganography

List for learning image steganography

• 

ASDL-GAN (Automatic steganographic distortion learning using a generative adversarial network):

UT-GAN (An embedding cost learning framework using GAN):

JS-GAN (Towards automatic embedding cost learning for JPEG steganography):

Wu's (GAN-based steganography with the concatenation of multiple feature maps):

UMC-GAN (A stable GAN for image steganography with multi-order feature fusion)

Steg-GMAN (Steganography Embedding Cost Learning with Generative Multi-Adversarial Network):

Dynamic Cost Correction (Multi-modality ensemble distortion for spatial steganography with dynamic cost correction)

Huang's (Automatic Asymmetric Embedding Cost Learning via Generative Adversarial Networks)

Tang's (An Embedded Cost Learning Framework Based on Cumulative Gradient Rewards)

ARES (ARES: On adversarial robustness enhancement for image steganographic cost learning):

• 

SGAN (Steganographic generative adversarial networks):

SSGAN (SSGAN: secure steganography based on generative adversarial networks):

• 

CEOA-GAN (High-Capacity Steganography Using Object Addition-based Cover Enhancement for Secure Communication in Networks):

• 

Xie's (A novel gradient-guided post-processing method for adaptive image steganography):

• 

Cost reassignment for improving security of adaptive steganography using an artificial immune system

CR-AIS (Constructing Immune-cover for Improving Holistic Security of Spatial Adaptive Steganography)

---

• 

Zhang's (Adversarial examples against deep neural network based steganalysis):

SPS-ENH (Adversarial steganography based on sparse cover enhancement)

CAAS (Improving security for image steganography using content-adaptive adversarial perturbations)

• 

ADV-EMB (CNN-based adversarial embedding for image steganography):

AEN (Adaptive spatial steganography based on adversarial examples):

JS-IAE (Enhancing JPEG steganography using iterative adversarial examples):

Bernard's (Explicit optimization of min max steganographic game):

ITE-SYN (Image steganography based on iterative adversarial perturbations onto a synchronized-directions sub-image):

Liu's (A New Adversarial Embedding Method for Enhancing Image Steganography):

Backpack (Backpack: A backpropagable adversarial embedding scheme):

Liu's (Adversarial robust image steganography against lossy JPEG compression)

AMP (Enhancing image steganography via adversarial optimization of the stego distribution)

Ma's (Enhancing the security of image steganography via multiple adversarial networks and channel attention modules)

Wang's (Enhancing Adversarial Embedding based Image Steganography via Clustering Modification Directions)

SGS (Adversarial steganography embedding via stego generation and selection)

---

MCTSteg (MCTSteg: A Monte Carlo tree search-based reinforcement learning framework for universal non-additive steganography):

SPAR-RL (An automatic cost learning framework for image steganography using deep reinforcement learning):

JEC-RL (Improving cost learning for JPEG steganography by exploiting JPEG domain knowledge)

PICO-RL (Payload-independent direct cost learning for image steganography)

JoPoL (Reinforcement learning of non-additive joint steganographic embedding costs with attention mechanism)

ReLOAD (ReLOAD: Using reinforcement learning to optimize asymmetric distortion for additive steganography)

RLAE (Content-adaptive Adversarial Embedding for Image Steganography Using Deep Reinforcement Learning)

---

PARIS (Provably Secure Robust Image Steganography)

Zhang's (Provably Secure Public-Key Steganography Based on Elliptic Curve Cryptography)

---

HUGO (Using high-dimensional image models to perform highly undetectable steganography):

WOW (Designing steganographic distortion using directional filters):

S-UNIWARD (Universal distortion function for steganography in an arbitrary domain):

HILL (A new cost function for spatial image steganography)

---

MiPOD (Content-Adaptive Steganography by Minimizing Statistical Detectability):

J-MiPOD (Efficient Steganography in JPEG Images by Minimizing Performance of Optimal Detector):

MVG (Improving Steganographic Security by Synchronizing the Selection Channel):

MG (Content-Adaptive Pentary Steganography Using the Multivariate Generalized Gaussian Cover Model):

---

CMD (A strategy of clustering modification directions in spatial image steganography):

SMD (Improving steganographic security by synchronizing the selection channel):

---

Gibbs(Gibbs construction in steganography):

STC(Minimizing Additive Distortion in Steganography Using Syndrome-Trellis Codes):

SPC (Designing near-optimal steganographic codes in practice based on polar codes)