paper-with-me

홈 › Papers

Steganographic Embeddings as an Effective Data Augmentation

2025-02-21 · Nicholas DiSalvo

Image Steganography is a cryptographic technique that embeds secret information into an image, ensuring the hidden data remains undetectable to the human eye while preserving the image's original visual integrity. Least Significant Bit (LSB) Steganography achieves this by replacing the k least significant bits of an image with the k most significant bits of a secret image, maintaining the appearance of the original image while simultaneously encoding the essential elements of the hidden data. In this work, we shift away from conventional applications of steganography in deep learning and explore its potential from a new angle. We present experimental results on CIFAR-10 showing that LSB Steganography, when used as a data augmentation strategy for downstream computer vision tasks such as image classification, can significantly improve the training efficiency of deep neural networks. It can also act as an implicit, uniformly discretized piecewise linear approximation of color augmentations such as (brightness, contrast, hue, and saturation), without introducing additional training overhead through a new joint image training regime that disregards the need for tuning sensitive augmentation hyperparameters.

📄 PDF Abstract BibTeX arXiv:2502.15245

Code (1)

nickd16/steganographic-augmentations 공식 구현 pytorch

Tasks

Data Augmentationimage-classificationImage ClassificationImage Steganography

Similar Papers 제목 키워드 기반

Continual Learning for Steganalysis

2022-09-03 · Zihao Yin, Ruohan Meng, Zhili Zhou

To detect the existing steganographic algorithms, recent steganalysis methods usually train a Convolutional Neural Network (CNN) model on the dataset consisting of corresponding paired cover/stego-images. However, it is …

Continual LearningSteganalysis

Purified and Unified Steganographic Network

2024-02-27 · CVPR 2024 1 · Guobiao Li, Sheng Li, Zicong Luo, Zhenxing Qian 외

Steganography is the art of hiding secret data into the cover media for covert communication. In recent years, more and more deep neural network (DNN)-based steganographic schemes are proposed to train steganographic net…

DenoisingImage Denoising

CNN-Assisted Steganography -- Integrating Machine Learning with Established Steganographic Techniques

2023-04-25 · Andrew Havard, Theodore Manikas, Eric C. Larson, Mitchell A. Thornton

We propose a method to improve steganography by increasing the resilience of stego-media to discovery through steganalysis. Our approach enhances a class of steganographic approaches through the inclusion of a steganogra…

Steganalysis

StegaVAR: Privacy-Preserving Video Action Recognition via Steganographic Domain Analysis

2025-12-14 · Lixin Chen, Chaomeng Chen, Jiale Zhou, Zhijian Wu 외 arxiv

Despite the rapid progress of deep learning in video action recognition (VAR) in recent years, privacy leakage in videos remains a critical concern. Current state-of-the-art privacy-preserving methods often rely on anony…

Action Recognition

Steganography of Steganographic Networks

2023-02-28 · Guobiao Li, Sheng Li, Meiling Li, Xinpeng Zhang 외

Steganography is a technique for covert communication between two parties. With the rapid development of deep neural networks (DNN), more and more steganographic networks are proposed recently, which are shown to be prom…