E2E-Steg: End-to-End Image Steganography via LLM-Driven Prompt Optimization and Multi-Scale Feature Fusion
- 1 November 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (11) , 17438-17454
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (62576100)
- Open Project of the Engineering Research Center of Autonomous Unmanned System Technology, Ministry of Education (zzwr202501)
- Big Data Computing Center of Southeast University
This publication has 53 references indexed in Scilit:
- AttenHideNet: A novel deep learning-based image steganography method using a lightweight U-net with soft attentionApplied Soft Computing, 2025
- Image steganography with high embedding capacity based on multi-target adversarial attackEngineering Applications of Artificial Intelligence, 2025
- PRIS: Practical robust invertible network for image steganographyEngineering Applications of Artificial Intelligence, 2024
- AFcIHNet: Attention feature-constrained network for single image information hidingEngineering Applications of Artificial Intelligence, 2023
- HiDDeN: Hiding Data With Deep Networks2018
- SSGAN: Secure Steganography Based on Generative Adversarial Networks2018
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Microsoft COCO: Common Objects in Context2014
- Multibit Embedding Algorithm for Steganography of Palette-Based Images2014
- Multi Bit Plane Image Steganography2006