Lemok00/IDEAS
Official pytorch implementation of paper "Image Disentanglement Autoencoder for Steganography without Embedding" (CVPR2022).
This project offers a new way to hide secret messages within images without embedding them directly, making it immune to traditional detection methods. You provide an original image and a secret message, and it generates a new, altered image that subtly conceals the information. This is useful for individuals or organizations needing to transmit confidential image-based data securely without it being flagged as hidden.
No commits in the last 6 months.
Use this if you need to securely send secret information embedded within an image, and you are concerned about advanced steganalysis tools detecting the hidden message.
Not ideal if you simply need to compress an image, or if you need to embed data in a non-image format.
Stars
52
Forks
8
Language
Python
License
—
Category
Last pushed
Nov 16, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Lemok00/IDEAS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
OPTML-Group/Unlearn-Saliency
[ICLR24 (Spotlight)] "SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in...
Shilin-LU/VINE
[ICLR 2025] "Robust Watermarking Using Generative Priors Against Image Editing: From...
WindVChen/DiffAttack
An unrestricted attack based on diffusion models that can achieve both good transferability and...
koninik/DiffusionPen
Official PyTorch Implementation of "DiffusionPen: Towards Controlling the Style of Handwritten...
Wuyxin/DISC
(ICML 2023) Discover and Cure: Concept-aware Mitigation of Spurious Correlation